AI-Powered Intelligence Synthesis—where network insights become comprehensive intelligence reports.

Most people talk about AI agents like they’re already reliable. They aren’t. They follow instructions. They spit out results. But they forget what they did, why it mattered, or how circumstances have changed. There’s no continuity. No memory. No grasp of unfolding context. Today’s agents can respond - but they can’t reflect, reason, or adapt over time. OpenAI’s new cookbook Temporal Agents with Knowledge Graphs lays out just how limiting that is and offers a credible path forward. It introduces a new class of temporal agents: systems built not around isolated prompts, but around structured, persistent memory. At the core is a knowledge graph that acts as an evolving world model - not a passive record, but a map of what happened, why it mattered, and what it connects to. This lets agents handle questions like: “What changed since last week?” “Why was this decision made?” “What’s still pending and what’s blocking it?” It’s an architectural shift that turns time, intent, and interdependence into first-class elements. This mirrors Tony Seale’s argument about enterprise data: most data products don’t fail because of missing pipelines - they fail because they don’t align with how the business actually thinks. Data lives in tables and schemas. Business lives in concepts like churn, margin erosion, customer health, or risk exposure. Tony’s answer is a business ontology: a formal, machine-readable layer that defines the language of the business and anchors data products to it. It’s a shift from structure to semantics - from warehouse to shared understanding. That’s the same shift OpenAI is proposing for agents. In both cases, what’s missing isn’t infrastructure. It’s interpretation. The challenge isn’t access. It’s alignment. If we want agents that behave reliably in real-world settings, it’s not enough to fine-tune them on PDFs or dump Slack threads into context windows. They need to be wired into shared ontologies - concept-level scaffolding like: Who are our customers? What defines success? What risks are emerging, and how are they evolving? The temporal knowledge graph becomes more than just memory. It becomes an interface - a structured bridge between reasoning and meaning. This goes far beyond another agent orchestration blueprint. It points to something deeper: Without time and meaning, there is no true delegation. We don’t need agents that mimic tasks. We need agents that internalise context and navigate change. That means building systems that don’t just handle data, but understand how it fits into the changing world we care about. OpenAI’s temporal memory graphs and Tony’s business ontologies aren’t separate ideas. They’re converging on the same missing layer: AI that reasons in the language of time and meaning. H/T Vin Vashishta for the pointer to the OpenAI cookbook, and image nicked from Tony (as usual). | 72 comments on LinkedIn

Over two years ago, I wrote about the emerging synergy between LLMs and ontologies - and how, together, they could create a self-reinforcing loop of continuous improvement. That post struck a chord. With GPT-5 now here, it’s the right moment to revisit the idea. Back then, GPT-3.5 and GPT-4 could draft ontology structures, but there were limits in context, reasoning, and abstraction. With GPT-5 (and other frontier models), that’s changing: 🔹 Larger context windows let entire ontologies sit in working memory at once.   🔹 Test-time compute enables better abstraction of concepts.   🔹 Multimodal input can turn diagrams, tables, and videos into structured ontology scaffolds.   🔹 Tool use allows ontologies to be validated, aligned, and extended in one flow. But some fundamentals remain. GPT-5 is still curve-fitting to a training set - and that brings limits: 🔹 The flipside of flexibility is hallucination. OpenAI has reduced it, but GPT-5 still scores 0.55 on SimpleQA, with a 5% hallucination rate on its own public-question dataset.   🔹 The model is bound by the landscape of its training data. That landscape is vast, but it excludes your private, proprietary data - and increasingly, an organisation’s edge will track directly to the data it owns outside that distribution. Fortunately, the benefits flow both ways. LLMs can help build ontologies, but ontologies and knowledge graphs can also help improve LLMs. The two systems can work in tandem.   Ontologies bring structure, consistency, and domain-specific context.   LLMs bring adaptability, speed, and pattern recognition that ontologies can’t achieve in isolation.   Each offsets the other’s weaknesses - and together they make both stronger. The feedback loop is no longer theory - we’ve been proving it:   Better LLM → Better Ontology → Better LLM - in your domain. There is a lot of hype around AI. GPT-5 is good, but not ground-breaking. Still, the progress over two years is remarkable. For the foreseeable future, we are living in a world where models keep improving - but where we must pair classic formal symbolic systems with these new probabilistic models. For organisations, the challenge is to match growing model power with equally strong growth in the power of their proprietary symbolic formalisation. Not all formalisations are equal. We want fewer brittle IF statements buried in application code, and more rich, flexible abstractions embedded in the data itself. That’s what ontologies and knowledge graphs promise to deliver. Two years ago, this was a hopeful idea.   Today, it’s looking less like a nice-to-have…   …and more like the only sensible way forward for organisations. ⭕ Neural-Symbolic Loop: https://lnkd.in/eJ7S22hF 🔗 Turn your data into a competitive edge: https://lnkd.in/eDd-5hpV

palantir hit $175/share because they understand what 99% of AI companies don't: ontologies. in 2021, the word "ontology" appeared 0 times in their earnings calls. by Q3 2024? 9 times. their US commercial revenue is growing 153% YoY. why? because LLMs are becoming the commodity, while ontologies are becoming the moat. let me explain why most enterprise AI initiatives are failing without one: every enterprise has the same problem: 47 different systems ❗️ 19 definitions of "customer" ❗️ 34 versions of "product"❗️ business logic scattered across 100+ applications ❗️ you throw AI at something like this? it hallucinates. but if you build an ontology first? it gains the context and data depth to be able to reason. palantir figured this out years ago. but here's what palantir doesn't do: verticalize at scale. they're brilliant at defense, government, contracting. but specialized industries need specialized ontologies. take telecommunications. a telco's "customer" isn't just a record - it's: ➕ a subscriber with multiple services ➕ a hierarchy of accounts and sub-accounts ➕ real-time network states ➕ billing cycles across geographies ➕ regulatory compliance per jurisdiction Orgs have tried to standardize this before. but standards aren't ontologies. they're just vocabularies. this is why Totogi has spent so much time and effort building their telco-specific ontology layer while palantir was perfecting horizontal enterprise ontologies, we went deep on telecom's unique semantic complexity. now telcos can deploy AI that takes one action - 'activate new customer' - and correctly translates it across systems that call it 'create subscriber' (BSS), 'provision user' (network), 'establish account' (billing), and 'initialize profile' (CRM). No more manual steps, no more dropped handoffs between systems. palantir proved the model. but they can't be everywhere. the future belongs to industry-specific semantic platforms like Totogi's BSS Magic 🚀 | 18 comments on LinkedIn

Introduction

Workshop from @FalkorDB and ZEP (Graphiti): Building Production Knowledge Graphs from Structured/Unstructured Data Sources.👩‍💻 Google Collab for the demo:...

Temporal Agents with Knowledge Graphs Executive Summary 1.1. Purpose and Audience 1.2. Key Takeaways How to Use this Cookbook...

Jessica Talisman has been publishing a series of articles on Substack about how to develop more robust AI systems by leveraging vocabularies, thesauri, tax...

Graph-R1 New RAG framework just dropped! Combines agents, GraphRAG, and RL. Here are my notes: Introduces a novel RAG framework that moves beyond traditional one-shot or chunk-based retrieval by integrating graph-structured knowledge, agentic multi-turn interaction, and RL. Graph-R1 is an agent that reasons over a knowledge hypergraph environment by iteratively issuing queries and retrieving subgraphs using a multi-step “think-retrieve-rethink-generate” loop. Unlike prior GraphRAG systems that perform fixed retrieval, Graph-R1 dynamically explores the graph based on evolving agent state. Retrieval is modeled as a dual-path mechanism: entity-based hyperedge retrieval and direct hyperedge similarity, fused via reciprocal rank aggregation to return semantically rich subgraphs. These are used to ground subsequent reasoning steps. The agent is trained end-to-end using GRPO with a composite reward that incorporates structural format adherence and answer correctness. Rewards are only granted if reasoning follows the proper format, encouraging interpretable and complete reasoning traces. On six RAG benchmarks (e.g., HotpotQA, 2WikiMultiHopQA), Graph-R1 achieves state-of-the-art F1 and generation scores, outperforming prior methods including HyperGraphRAG, R1-Searcher, and Search-R1. It shows particularly strong gains on harder, multi-hop datasets and under OOD conditions. The authors find that Graph-R1’s performance degrades sharply without its three key components: hypergraph construction, multi-turn interaction, and RL. Ablation study supports that graph-based and multi-turn retrieval improves information density and accuracy, while end-to-end RL bridges the gap between structure and language. Paper: https://lnkd.in/eGbf4HhX | 15 comments on LinkedIn

Alhamdulillah, iText2KG v0.0.8 is finally out! (Yes, I’ve been quite busy these past few months 😅) .. and it can now build dynamic knowledge graphs. The GIF below shows a dynamic KG generated from OpenAI tweets between June 18 and July 17. (Note: Temporal/logical conflicts aren't handled yet in this version, but you can still resolve them with a post-processing filter.) Here are the main updated features: - iText2KG_Star: Introduced a simpler and more efficient version of iText2KG that eliminates the separate entity extraction step. Instead of extracting entities and relations separately, iText2KG_Star directly extracts triplets from text. This approach is more efficient as it reduces processing time and token consumption and does not need to handle invented/isolated entities. - Facts-Based KG Construction: Enhanced the framework with facts-based knowledge graph construction using the Document Distiller to extract structured facts from documents, which are then used for incremental KG building. This approach provides more exhaustive and precise knowledge graphs. - Dynamic Knowledge Graphs: iText2KG now supports building dynamic knowledge graphs that evolve. By leveraging the incremental nature of the framework and document snapshots with observation dates, users can track how knowledge changes and grows. Check out the new version and an example of OpenAI Dynamic KG Construction in the first comment.

Here, I clearly explain why businesses must transition from raw tabular data to RDF-based knowledge graphs, and why this is essential to ground AI in logic-driven, traceable inference rather than black-box prediction: 1. Your tabular data is dumb.

Scaling GraphRAG to Millions of Documents: Lessons from the SIGIR 2025 LiveRAG Challenge 👉 WHY THIS MATTERS Retrieval-augmented generation (RAG) struggles with multi-hop questions that require connecting information across documents. While graph-based RAG methods like GEAR improve reasoning by structuring knowledge as entity-relationship triples, scaling these approaches to web-sized datasets (millions/billions of documents) remains a bottleneck. The culprit? Traditional methods rely heavily on LLMs to extract triples—a process too slow and expensive for large corpora. 👉 WHAT THEY DID Researchers from Huawei and the University of Edinburgh reimagined GEAR to sidestep costly offline triple extraction. Their solution: - Pseudo-alignment: Link retrieved passages to existing triples in Wikidata via sparse retrieval. - Iterative expansion: Use a lightweight LLM (Falcon-3B-Instruct) to iteratively rewrite queries and retrieve additional evidence through Wikidata’s graph structure. - Multi-step filtering: Combine Reciprocal Rank Fusion (RRF) and prompt-based filtering to reconcile noisy alignments between Wikidata and document content. This approach achieved 87.6% correctness and 53% faithfulness on the SIGIR 2025 LiveRAG benchmark, despite challenges in aligning Wikidata’s generic triples with domain-specific document content. 👉 KEY INSIGHTS 1. Trade-offs in alignment: Linking Wikidata triples to documents works best for general knowledge but falters with niche topics (e.g., "Pacific geoduck reproduction" mapped incorrectly to oyster biology). 2. Cost efficiency: Avoiding LLM-based triple extraction reduced computational overhead, enabling scalability. 3. The multi-step advantage: Query rewriting and iterative retrieval improved performance on complex questions requiring 2+ reasoning hops. 👉 OPEN QUESTIONS - How can we build asymmetric semantic models to better align text and graph data? - Can hybrid alignment strategies (e.g., blending domain-specific KGs with Wikidata) mitigate topic drift? - Does graph expansion improve linearly with scale, or are diminishing returns inevitable? Why read this paper? It’s a pragmatic case study in balancing scalability with reasoning depth in RAG systems. The code and prompts are fully disclosed, offering a blueprint for adapting GraphRAG to real-world, large-scale applications. Paper: "Millions of G∈AR-s: Extending GraphRAG to Millions of Documents" (Shen et al., SIGIR 2025). Preprint: arXiv:2307.17399.

Why a semantic layer provides the contextual enrichment for effective data utilization and prepares your enterprise for the future of AI.

I've spent long, hard years learning how to talk about knowledge graphs and semantics with software engineers who have little training in linguistics. I feel quite fluent at this point, after investing huge amounts of effort into understanding statistics (I was a humanities undergrad) and into unpac

How organizations must shift from data-driven to knowledge-driven approaches with knowledge graph powered semantic layers

What’s the difference between context engineering and ontology engineering? We hear a lot about “context engineering” these days in AI wonderland. A lot of good thing are being said but it’s worth noting what’s missing. Yes, context matters. But context without structure is narrative, not knowledge. And if AI is going to scale beyond demos and copilots into systems that reason, track memory, and interoperate across domains… then context alone isn’t enough. We need ontology engineering. Here’s the difference: - Context engineering is about curating inputs: prompts, memory, user instructions, embeddings. It’s the art of framing. - Ontology engineering is about modeling the world: defining entities, relations, axioms, and constraints that make reasoning possible. In other words: Context guides attention. Ontology shapes understanding. What’s dangerous is that many teams stop at context, assuming that if you feed the right words to an LLM, you’ll get truth, traceability, or decisions you can trust. This is what I call “hallucination of control”. Ontologies provide what LLMs lack: grounding, consistency, and interoperability, but they are hard to build without the right methods, adapted from the original discipline that started 20+ years ago with the semantic web, now it’s time to work it out for the LLM AI era. If you’re serious about scaling AI across business processes or mission-critical systems, the real challenge is more than context, it’s shared meaning. And tech alone cannot solve this. That’s why we need put ontology discussion in the board room, because integrating AI into organizations is much more complicated than just providing the right context in a prompt or a context window. That’s it for today. More tomorrow! I’m trying to get back at journaling here every day. 🤙 hope you will find something useful in what I write. | 71 comments on LinkedIn

𝙏𝙝𝙤𝙪𝙜𝙝𝙩 𝙛𝙤𝙧 𝙩𝙝𝙚 𝙙𝙖𝙮: I've been mulling over how both OWL and SHACL can be employed during the decision-making phase for AI Agents when using a knowledge graph instead of relying on an LLM that hallucinates. In this way, the LLM can still be used for assessment and sensory feedback, but it augments the graph, not the other way around. OWL and SHACL serve different roles. SHACL is not just a preprocessing validator; it can play an active role in constraining, guiding, or triggering decisions, especially when integrated into AI pipelines. However, OWL is typically more central to inferencing and reasoning tasks. SHACL can actively participate in decision-making, especially when decisions require data integrity, constraint enforcement, or trigger-based logic. In complex agents, OWL provides the inferencing engine, while SHACL acts as the constraint gatekeeper and occasionally contributes to rule-based decision-making. For example, an AI agent processes RDF data describing an applicant's skills, degree, and experience. SHACL validates the data's structure, ensuring required fields are present and correctly formatted. OWL reasoning infers that the applicant is qualified for a technical role and matches the profile of a backend developer. SHACL is then used again to check policy compliance. With all checks passed, the applicant is shortlisted, and a follow-up email is triggered. In AI agent decision-making, OWL and SHACL often work together in complementary ways. SHACL is commonly used as a preprocessing step to validate incoming RDF data. If the data fails validation, it's flagged or excluded, ensuring only clean, structurally sound data reaches the OWL reasoner. In this role, SHACL acts as a gatekeeper. They can also operate in parallel or in an interleaved manner within a pipeline. As decisions evolve, SHACL shapes may be checked mid-process. Some AI agents even use SHACL as a rule engine—to trigger alerts, detect actionable patterns, or constrain reasoning paths—while OWL continues to handle more complex semantic inferences, such as class hierarchies or property logic. Finally, SHACL can augment decision-making by confirming whether OWL-inferred actions comply with specific constraints. OWL may infer that “A is a type of B, so do X,” and SHACL then determines whether doing X adheres to a policy or requirement. Because SHACL supports closed-world assumptions (which OWL does not), it plays a valuable role in enforcing policies or compliance rules during decision execution. Illustrated:

It’s already the end of Sunday — I hope you all had a wonderful week. Mine was exceptionally busy, with the GUG seminar and the upcoming tutorial preparation. I usually take time for a personal…

I'm trying to build a Knowledge Graph. Our team has done experiments with current libraries available (𝐋𝐥𝐚𝐦𝐚𝐈𝐧𝐝𝐞𝐱, 𝐌𝐢𝐜𝐫𝐨𝐬𝐨𝐟𝐭'𝐬 𝐆𝐫𝐚𝐩𝐡𝐑𝐀𝐆, 𝐋𝐢𝐠𝐡𝐫𝐚𝐠, 𝐆𝐫𝐚𝐩𝐡𝐢𝐭𝐢 etc.) From a Product perspective, they seem to be missing the basic, common-sense features. 𝐒𝐭𝐢𝐜𝐤 𝐭𝐨 𝐚 𝐅𝐢𝐱𝐞𝐝 𝐓𝐞𝐦𝐩𝐥𝐚𝐭𝐞: My business organizes information in a specific way. I need the system to use our predefined entities and relationships, not invent its own. The output has to be consistent and predictable every time. 𝐒𝐭𝐚𝐫𝐭 𝐰𝐢𝐭𝐡 𝐖𝐡𝐚𝐭 𝐖𝐞 𝐀𝐥𝐫𝐞𝐚𝐝𝐲 𝐊𝐧𝐨𝐰: We already have lists of our products, departments, and key employees. The AI shouldn't have to guess this information from documents. I want to seed this this data upfront so that the graph can be build on this foundation of truth. 𝐂𝐥𝐞𝐚𝐧 𝐔𝐩 𝐚𝐧𝐝 𝐌𝐞𝐫𝐠𝐞 𝐃𝐮𝐩𝐥𝐢𝐜𝐚𝐭𝐞𝐬: The graph I currently get is messy. It sees "First Quarter Sales" and "Q1 Sales Report" as two completely different things. This is probably easy but want to make sure this does not happen. 𝐅𝐥𝐚𝐠 𝐖𝐡𝐞𝐧 𝐒𝐨𝐮𝐫𝐜𝐞𝐬 𝐃𝐢𝐬𝐚𝐠𝐫𝐞𝐞: If one chunk says our sales were $10M and another says $12M, I need the library to flag this disagreement, not just silently pick one. It also needs to show me exactly which documents the numbers came from so we can investigate. Has anyone solved this? I'm looking for a library —that gets these fundamentals right. | 21 comments on LinkedIn

❓ Why I Wrote This Book? In the past two to three years, we've witnessed a revolution. First with ChatGPT, and now with autonomous AI agents. This is only the beginning. In the years ahead, AI will transform not only how we work but how we live. At the core of this transformation lies a single breakthrough technology: large language models (LLMs). That’s why I decided to write this book. This book explores what an LLM is, how it works, and how it develops its remarkable capabilities. It also shows how to put these capabilities into practice, like turning an LLM into the beating heart of an AI agent. Dissatisfied with the overly simplified or fragmented treatments found in many current books, I’ve aimed to provide both solid theoretical foundations and hands-on demonstrations. You'll learn how to build agents using LLMs, integrate technologies like retrieval-augmented generation (RAG) and knowledge graphs, and explore one of today’s most fascinating frontiers: multi-agent systems. Finally, I’ve included a section on open research questions (areas where today’s models still fall short, ethical issues, doubts, and so on), and where tomorrow’s breakthroughs may lie. 🧠 Who is this book for? Anyone curious about LLMs, how they work, and how to use them effectively. Whether you're just starting out or already have experience, this book offers both accessible explanations and practical guidance. It's for those who want to understand the theory and apply it in the real world. 🛑 Who is this book not for? Those who dismiss AI as a passing fad or have no interest in what lies ahead. But for everyone else this book is for you. Because AI agents are no longer speculative. They’re real, and they’re here. A huge thanks to my co-author Gabriele Iuculano, and the Packt's team: Gebin George, Sanjana Gupta, Ali A., Sonia Chauhan, Vignesh Raju., Malhar Deshpande #AI #LLMs #KnowledgeGraphs #AIagents #RAG #GenerativeAI #MachineLearning #NLP #Agents #DeepLearning | 22 comments on LinkedIn

A full working Cypher script that simulates a Tendering System with multiple workflows, AI agent interactions, conversations, approvals, and more — all modeled and executed natively in a Graph.

This blog post provides a hands-on guide for AI engineers and developers on how to build an initial KYC agent prototype with the OpenAI Agents SDK. We'll explore how to equip our agent with a suite of tools (including MCP Server tools) to uncover and investigate potential fraud patterns.

Transform Claude's Hidden Memory Into Interactive Knowledge Graphs Universal tool to visualize any Claude user's memory.json in beautiful interactive graphs. Transform your Claude Memory MCP data into stunning interactive visualizations to see how your AI assistant's knowledge connects and evolves over time. Enterprise teams using Claude lack visibility into how their AI assistant accumulates and organizes institutional knowledge. Claude Memory Viz provides zero-configuration visualization that automatically finds memory files and displays 72 entities with 93 relationships in real-time force-directed layouts. Teams can filter by entity type, search across all data, and explore detailed connections through rich tooltips. The technical implementation supports Claude's standard NDJSON memory format, automatically detecting and color-coding entity types from personality profiles to technical tools. Node size reflects connection count, while adjustable physics parameters enable optimal spacing for large knowledge graphs. Built with Cytoscape.js for performance optimization. Built with the philosophy "Solve it once and for all," the tool works for any Claude user with zero configuration. The visualizer automatically searches common memory file locations, provides demo data fallback, and offers clear guidance when files aren't found. Integration requires just git clone and one command execution. This matters because AI memory has been invisible to users, creating trust and accountability gaps in enterprise AI deployment. When teams can visualize how their AI assistant organizes knowledge, they gain insights into decision-making patterns and can optimize their AI collaboration strategies. 👩‍💻https://lnkd.in/e__RQh_q | 10 comments on LinkedIn

Get this comprehensive guide from Manning on how to build a GraphRAG system from scratch. Available now for free!

This is it. This is the conversation every leadership team needs to be having right now. "The Orchestration Graph" by WRITER product leader Matan-Paul Shetrit linked in comments is a must-read. The primary constraint on business is no longer execution. It's supervision. For a century, we built companies to overcome the high cost of getting things done. We built hierarchies, departments, and complex processes — all to manage labor-intensive execution. That era is over. With AI agents, execution is becoming abundant, on-demand, and programmatic. The new bottleneck is our ability to direct, govern, and orchestrate this immense new capacity. The firm is evolving from a factory into an "operating system." Your ORG CHART is no longer the map. The real map is the Orchestration Graph: the dynamic, software-defined network of humans, models, and agents that actually does the work. This isn't just a new tool or a productivity hack. It's a fundamental rewiring of the enterprise. It demands we rethink everything: Structure: How do we manage systems, not just people? Strategy: What work do we insource to our agentic "OS" versus outsource to models-as-a-service? Metrics: Are we still measuring human activity, or are we measuring system throughput and intelligence? This is the WRITER call to arms: The companies that win won't just adopt AI; they will restructure themselves around it. They will build their own Orchestration Graph, with governance and institutional memory at the core. They will treat AI not as a feature, but as the new foundation. At WRITER, this is the future we are building every single day — giving companies the platform to create their own secure, governed, and intelligent orchestration layer. The time to act is now. Read the article. Start the conversation with your leaders. And begin rewiring your firm. | 37 comments on LinkedIn

When people discuss how LLMS "reason," you’ll often hear that they rely on transduction rather than abduction. It sounds technical, but the distinction matters - especially as we start wiring LLMs into systems that are supposed to think. 🔵 Transduction is case-to-case reasoning. It doesn’t build theories; it draws fuzzy connections based on resemblance. Think: “This metal conducts electricity, and that one looks similar - so maybe it does too.” 🔵 Abduction, by contrast, is about generating explanations. It’s what scientists (and detectives) do: “This metal is conducting - maybe it contains free electrons. That would explain it.” The claim is that LLMs operate more like transducers - navigating high-dimensional spaces of statistical similarity, rather than forming crisp generalisations. But this isn’t the whole picture. In practice, it seems to me that LLMs also perform a kind of induction - abstracting general patterns from oceans of text. They learn the shape of ideas and apply them in novel ways. That’s closer to “All metals of this type have conducted in the past, so this one probably will.” Now add tools to the mix - code execution, web search, Elon Musk's tweet history 😉 - and LLMs start doing something even more interesting: program search and synthesis. It's messy, probabilistic, and not at all principled or rigorous. But it’s inching toward a form of abductive reasoning. Which brings us to a more principled approach for reasoning within an enterprise domain: the neuro-symbolic loop - a collaboration between large language models and knowledge graphs. The graph provides structure: formal semantics, ontologies, logic, and depth. The LLM brings intuition: flexible inference, linguistic creativity, and breadth. One grounds. The other leaps. 💡 The real breakthrough could come when the grounding isn’t just factual, but conceptual - when the ontology encodes clean, meaningful generalisations. That’s when the LLM’s leaps wouldn’t just reach further - they’d rise higher, landing on novel ideas that hold up under formal scrutiny. 💡 So where do metals fit into this new framing? 🔵 Transduction: “This metal conducts. That one looks the same - it probably does too.” 🔵 Induction: “I’ve tested ten of these. All conducted. It’s probably a rule.” 🔵 Abduction: “This metal is conducting. It shares properties with the ‘conductive alloy’ class - especially composition and crystal structure. The best explanation is a sea of free electrons.” LLMs, in isolation, are limited in their ability to perform structured abduction. But when embedded in a system that includes a formal ontology, logical reasoning, and external tools, they can begin to participate in richer forms of reasoning. These hybrid systems are still far from principled scientific reasoners - but they hint at a path forward: a more integrated and disciplined neuro-symbolic architecture that moves beyond mere pattern completion.

🚀 When I shared our 2025 goals for the Enterprise Data Organization, one of the things I alluded to was machine-readable column-level metadata. Let’s unpack what that means—and why it matters. 🔍 What: For datasets we deliver via modern cloud distribution, we now provide human - and machine - readable metadata at the column level. Each column has an immutable URL (no auth, no CAPTCHA) that hosts name/value metadata - synonyms, units of measure, descriptions, and more - in multiple human languages. It’s semantic context that goes far beyond what a traditional data dictionary can convey. We can't embed it, so we link to it. 💡 Why: Metadata is foundational to agentic, precise consumption of structured data. Our customers are investing in semantic layers, data catalogs, and knowledge graphs - and they shouldn’t have to copy-paste from a PDF to get there. Use curl, Python, Bash - whatever works - to automate ingestion. (We support content negotiation and conditional GETs.) 🧠 Under the hood? It’s RDF. Love it or hate it, you don’t need to engage with the plumbing unless you want to. ✨ To our knowledge, this hasn’t been done before. This is our MVP. We’re putting it out there to learn what works - and what doesn’t. It’s vendor-neutral, web-based, and designed to scale across: 📊 Breadth of datasets across S&P 🧬 Depth of metadata 🔗 Choice of linking venue 🙏 It took a village to make this happen. I can’t name everyone without writing a book, but I want to thank our executive leadership for the trust and support to go build this. Let us know what you think! 🔗 https://lnkd.in/gbe3NApH Martina Cheung, Saugata Saha, Swamy Kocherlakota, Dave Ernsberger, Mark Eramo, Frank Tarsillo, Warren Breakstone, Hamish B., Erica Robeen, Laura Miller, Justine S Iverson, | 17 comments on LinkedIn

Part 6 of 6 in the series “LLMs Need Knowledge Graphs. Use RDF or End Up Rebuilding It.”