I'm getting pickier and pickier about what I want to call a knowledge graph. Or maybe I'm just getting grumpier.

A sophisticated knowledge graph memory system that stores interconnected information with rich semantic structure using Neo4j. - shuruheel/mcp-neo4j-shan

Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-labeled, created by...

Graph Exchange, Fall 2025 - Conference summary of Neo4j, Cognee, DeepLearning.AI and Letta

Why Large Graphs Fail to Understand Small Scalability We love to talk about scaling graphs: billions of nodes, trillions of relationships and distributed clusters. But, in practice, larger graphs often become harder to understand. As Labelled Property Graphs (LPGs) grow, their structure remains sound, but their meaning starts to drift. Queries still run, but the answers become useless. In my latest post, I explore why semantic coherence collapses faster than infrastructure can scale up, what 'cognitive coherence' really means in graph systems and how the flexibility of LPGs can empower and endanger knowledge integrity. Full article: 'Why Large Graphs Fail Small: When LPG Scalability Breaks Cognitive Coherence' https://lnkd.in/epmwGM9u #GraphRAG #KnowledgeGraph #LabeledPropertyGraph #LPG #SemanticAI #AIExplainability #GraphThinking #RDF #AKG #KGL | 15 comments on LinkedIn

From Siloed Data to Missed Opportunities Organizations today sit on massive troves of data – customer transactions, logs, metrics, documents – often scattered across departments and trapped in spreadsheets or relational tables. The data is diverse, dispersed, and growing at unfathomable rates, to th

Following yesterday's announcements from OpenAI, brands start to have real ways to operate inside ChatGPT. At a very high-level this is the map for anyone considering entering (or expanding) into the ChatGPT ecosystem: Conversational Prompts / UX: optimize how ChatGPT “asks” for or surfaces brand se

Is OpenAI quietly moving toward knowledge graphs? Yesterday’s OpenAI DevDay was all about new no-code tools to create agents. Impressive. But what caught my attention wasn’t what they announced… it’s what they didn’t talk about. During the summer, OpenAI released a Cookbook update introducing the concept Temporal Agents (see below) connecting it to Subject–Predicate–Object triples: the very foundation of a knowledge graph. If you’ve ever worked with graphs, you know this means something big: they’re not just building agents anymore they’re building memory, relationships, and meaning. When you see “London – isCapitalOf – United Kingdom” in their official docs, you realize they’re experimenting with how to represent knowledge itself. And with any good knowledge graph… comes an ontology. So here’s my prediction: ChatGPT-6 will come with a built-in graph that connects everything about you. The question is: do you want their AI to know everything about you? Or do you want to build your own sovereign AI, one that you own, built from open-source intelligence and collective knowledge? Would love to know what you think. Is that me hallucinating or is that a weak signal?👇 | 62 comments on LinkedIn

Please read the previous article on Vanilla RAG

Formal basics, real systems, and why industry favors property graphs while RDF remains important

A new AI-friendly database comes to Wikidata, Wikipedia’s sister project.

Called the Wikidata Embedding Project, the system applies a vector-based semantic search to the existing data on Wikipedia and its sister platforms, consisting of nearly 120 million entries.

Inspired by the talented Jessica Talisman, here is a new infographic microsim that you can use when teaching the step-by-step progression from a simple list of business terms to a real-time agentic enterprise knowledge graph: https://lnkd.in/g66HRBhn You can include this interactive microsim in all of your semantics/ontology and agentic AI courses with just a single line of HTML.

For all the excitement around large language models, the latest research from Simona-Vasilica Oprea and Georgiana Stănescu (Electronics 14:1313, 2025) offers a reality check. Automatic ontology generation, even with novel prompting techniques like Memoryless CQ-by-CQ and Ontogenia, remains a partial

Ever heard of "knowledge engineering"? It’s what we called AI before AI was cool. I just pulled this out of the deep archives, Stanford University, 1980. Feigenbaum’s HPP report. The bones of modern context engineering were already there. ↳ What they did: ➤ Curated knowledge bases, not giant prompts ➤ Rule “evocation” to gate relevance ➤ Certainty factors to track confidence ➤ Shells + blackboards to orchestrate tools ➤ Traceable logic so humans could audit decisions ↳ What we do now: ➤ Trimmed RAG context instead of bloated prompts ➤ Retrieval + reranking + policy checks for gating ➤ Scores, evals, and guardrails to manage uncertainty ➤ Tool calling, MCPs, workflow engines for execution ➤ Logs + decision docs for explainability ↳ The through-line for UX: ➤Performance comes from shaping context, what to include, when to include it, and how to prove it worked. If you're building AI agents, you're standing on those shoulders. Start with context, not cleverness. Follow for human-centered AI + UX. Reshare if your team ships with context discipline. | 41 comments on LinkedIn

Highlights of Mike Ferguson keynote at BDL: 1) AI agents are already everywhere so they need to be coordinated. 2) Structured/Unstructured data is converging. 3) Knowledge Graphs and Enterprise Ontology is the context for AI agents 4) Data products to enable reuse and 5) governance must be active. Mike is not just a true veteran in the data space, but also someone who can see the big picture when times of hype. His keynotes are always eye opening to see where the puck is heading. The following are the snippets from his slides which are packed with so much knowledge! 1) AI Agents - Challenges - There Has Been an Explosion of Al Agent Development Tools That is Leading to a Proliferation of Al Agents - A Federated Organisation Structure and Common Al Governance Are Needed to Coordinate Decentralised Development of Al Agents 2) Structured and Unstructured data. - Convergence of Structured Data and Analytics (data warehouse/lake) + Knowledge Management (content and record management systems) 3) Enterprise Ontology and Knowledge Graphs - Lots of Siloed Product Oriented Semantic Layers / Knowledge Graphs Are Now Emerging at All Levels to Provide Context to Solution Al Agents Before Using Tools to Get the Relevant Information. - Ideally Natural Language Queries Should Query an Enterprise Knowledge Graph First to Get Complete Context and Then Get the Relevant Information from Agents for Holistic Insights - Integrated metadata in an enterprise ontology to provide context for all Al will potentially become the most valuable capability of the Al era - Al Requirements - We Need to Create a Data Catalog & Vectorised Knowledge Graph to Know What Relevant Data Is Needed as Context to Answer Natural Language Queries - Issues With Providing Context for Al Over the Next Few Years - Chaos!! - We Need to Integrate Metadata to Provide Context for ALL Al Agents & the Amount of Metadata is Going to be BIG! - The BIG METADATA question: Will we use the same approach to create ontology subgraphs that can be connected to form an enterprise ontology and open it up to multiple Agents? - How Do You Enable Data for Al? - A New Metadata Layer Is Emerging In the Data and Al Stack Which Is Needed for the Agentic Enterprise! - The Enterprise Ontology Layer 4) Data Products - Foundational Data Products are Critical in Any Business and Can Be Reused to Create Others - Conversational Data Engineering Is Now Mainstream to Generate Pipelines to Produce Data Products for Each Entity Defined in the Business Glossary Within a Data Catalog 5) Active Governance - Data Governance Needs a Major Rethink - It Needs to be Active, Dynamic and Always On - The Agentic Unified Data Governance Platform - Al-Assisted Data Governance Services and Al-Agents Thanks Mike for sharing your knowledge!! What are your main takeaways? Also, he was a guest on Catalog & Cocktails Podcast so check that out (link in the comments). | 12 comments on LinkedIn

Most companies are building autonomous agents with LLMs at the center, making every decision. Here's the problem: each LLM call has a ~5% error rate. Chain 10 calls together and your reliability drops to 60%. ⁉️ Here's the math: Single LLM call = 95% accuracy. Chain 10 LLM calls for agentic workflow = 0.95^10 = 60% reliability. This compounds exponentially with complexity. Enterprise can't ship that. Some companies like Rippletide Yann BILIEN getting agents to production are doing something different. They're using graphs as the orchestration layer and pushing LLMs to the edges. The architectural solution is about removing LLMs from the orchestration loop entirely and using hypergraph-based reasoning substrates instead. Why hypergraphs specifically? Regular graphs connect two nodes per edge. Hyperedges connect multiple nodes simultaneously - critical for representing complex state transitions. A single sales conversation turn involves speaker, utterance, topic, customer state, sentiment, outcome, and timestamp. A hyperedge captures all these relationships atomically in the reasoning structure. The neurosymbolic integration is what makes this production-grade: Symbolic layer = business rules, ontologies, deterministic patterns. These are hard constraints that prevent policy violations (discount limits, required info collection, compliance rules). Neural layer = RL components that learn edge weights, validate patterns, update confidences. Operates within symbolic constraints. Together they enable the "crystallization mechanism" - patterns start probabilistic, validate through repeated success, then lock into deterministic rules at 95%+ confidence. The system becomes non-regressive: it learns and improves but validated patterns never degrade. Here's what this solves that LLM-orchestration can't: Hallucinations with confidence - eliminated because reasoning follows deterministic graph traversal through verified data, not generative token prediction. Goal drift - impossible because goal hierarchies are encoded in graph topology and enforced mathematically by traversal algorithms. Data leakage across contexts - prevented through graph partitioning and structural access controls, not prompt instructions. Ignoring instructions - doesn't happen because business rules are executable constraints, not natural language hopes. The LLM's role reduces to exactly two functions: (1) helping structure ontologies during build phase, (2) optionally formatting final outputs to natural language. Zero involvement in decision-making or orchestration. Rippletide's architecture demonstrates this at scale: Hypergraph stores unified memory + reasoning (no RAG, no retrieval bottleneck) Reasoning engines execute graph traversal algorithms for decisions Weighted edges encode relationship strength, recency, confidence, importance Temporal/spatial/causal relationships explicit in structure (what LLMs fundamentally lack) | 27 comments on LinkedIn

Some thoughts

The market is obsessed with the sexy stuff, autonomous agents, reasoning engines, sophisticated orchestration. Meanwhile, the unsexy foundation layer is completely broken. ⭕ And that foundation layer? It's the only thing that determines whether your agent actually works. Here's the technical problem killing agentic AI reliability and that a great company like Lettria solves: The document-to-knowledge-graph pipeline is fundamentally broken : Layer 1: Document Parsing Hell You can't feed a 400-page PDF with mixed layouts into a vision-language model and expect consistent structure. Here's why: Reading order detection fails on multi-column layouts, nested tables, and floating elements Vision LLMs hallucinate cell boundaries on complex tables (financial statements, technical specs) You need bbox-level segmentation with preserved coordinate metadata for traceability Traditional CV models (Doctr, Detectron2, YOLO) outperform transformers on layout detection and run on CPU Optimal approach requires model routing: PDF Plumber for text extraction, specialized table parsers for structured data, VLMs only as fallback Without preserving document_id → page_num → bbox_coords → chunk_id mapping, you lose provenance permanently Layer 2: Ontology Generation Collapse RDF/OWL ontology creation isn't prompt engineering. It's semantic modeling: You need 5-6 levels of hierarchical abstraction (not flat entity lists) Object properties require explicit domain/range specifications (rdfs:domain, rdfs:range) Data properties need typed constraints (xsd:string, xsd:integer, xsd:date) Relationships must follow semantic web standards (owl:ObjectProperty, owl:DatatypeProperty) LLM might output syntactically valid Turtle that violates semantic consistency Proper approach: 8-9 specialized LLM calls with constraint validation, reasoner checks, and ontologist-in-the-loop verification Without this, your knowledge graph has edges connecting semantically incompatible nodes Layer 3: Text-to-RDF Extraction Failure Converting natural language to structured triples while maintaining schema compliance is where frontier models crater: GPT-4/Claude achieve ~60-70% F1 on entity extraction, ~50-60% on relation extraction (measured on Text2KGBench) They hallucinate entities not in your ontology They create relations violating domain/range constraints Context window limitations force truncation (32K tokens = ~10-15 pages with full ontology) A specialized 600M parameter model fine-tuned on 14K annotated triples across 19 domain ontologies hits 85%+ F1 Why? Task-specific loss functions, schema-aware training, constrained decoding The compounding effect destroys reliability Your agent's reasoning is irrelevant when it's operating on a knowledge graph where 73% of nodes/edges are wrong, incomplete, or unverifiable. Without bidirectional traceability (SPARQL query → triple → chunk_id → bbox → source PDF), you can't deploy in regulated environments. Period. | 13 comments on LinkedIn

Building AI agents that can synthesize scattered knowledge like expert developers 🧠 I have a tutorial about building intelligent AI memory systems with Cognee in my 'Agents Towards Production' repo that solves a critical problem - developers navigate between documentation, community practices, and personal experience, but traditional approaches treat these as isolated resources. This tutorial shows how to build a unified knowledge graph that connects Python's design philosophy, real-world implementations from its creator, and your specific development patterns. The tutorial covers 3 key capabilities: - Knowledge Graph Construction: Building interconnected networks from Guido van Rossum's actual commits, PEP guidelines, and personal conversations - Temporal Analysis: Understanding how solutions evolved over time with time-aware queries - Dynamic Memory Layer: Inferring implicit rules and discovering non-obvious connections across knowledge domains The cross-domain discovery is particularly impressive - it connects your validation issues from January 2024 with Guido van Rossum's actual solutions from mypy and CPython. Rather than keyword matching, it understands semantic relationships between your type hinting challenges and historical solutions, even when terminology differs. Tech stack: - Cognee for knowledge graph construction - OpenAI GPT-4o-mini for entity extraction - Graph algorithms for pattern recognition - Vector embeddings for semantic search The system uses semantic graph traversal with deep relationship understanding for contextually aware responses. Includes working Python code, complete Jupyter notebook with interactive visualizations, and production-ready patterns. Part of the collection of practical guides for building production-ready AI systems. Direct link to the tutorial: https://lnkd.in/eSsjwbuh Ever wish you could query all your development knowledge as one unified intelligent system? ♻️ Repost to let your network learn about this too!

Is Graph Data Science a critical, transformative layer for GraphRAG? The field of enterprise Artificial Intelligence (AI) is undergoing a significant architectural evolution. The initial enthusiasm for Large Language Models (LLMs) has matured into a pragmatic recognition of their limitations, partic

What is your role? I am working in the Publications Office of the European Union as the team leader of the Reference data team. The Publications Office of the European Union is the official provider of publishing services to all EU institutions, bodies and agencies.

This research aims to investigate the roles of ontology and Semantic Web Technologies (SWT) in modern knowledge representation and data management. By analyzing a dataset of 10,037 academic articles from Web of Science (WoS) published in the last 6 years (2019–2024) across several fields, such as computer science, engineering, and telecommunications, our research identifies important trends in the use of ontologies and semantic frameworks. Through bibliometric and semantic analyses, Natural Language Processing (NLP), and topic modeling using Latent Dirichlet Allocation (LDA) and BERT-clustering approach, we map the evolution of semantic technologies, revealing core research themes such as ontology engineering, knowledge graphs, and linked data. Furthermore, we address existing research gaps, including challenges in the semantic web, dynamic ontology updates, and scalability in Big Data environments. By synthesizing insights from the literature, our research provides an overview of the current state of semantic web research and its prospects. With a 0.75 coherence score and perplexity = 48, the topic modeling analysis identifies three distinct thematic clusters: (1) Ontology-Driven Knowledge Representation and Intelligent Systems, which focuses on the use of ontologies for AI integration, machine interpretability, and structured knowledge representation; (2) Bioinformatics, Gene Expression and Biological Data Analysis, highlighting the role of ontologies and semantic frameworks in biomedical research, particularly in gene expression, protein interactions and biological network modeling; and (3) Advanced Bioinformatics, Systems Biology and Ethical-Legal Implications, addressing the intersection of biological data sciences with ethical, legal and regulatory challenges in emerging technologies. The clusters derived from BERT embeddings and clustering show thematic overlap with the LDA-derived topics but with some notable differences in emphasis and granularity. Our contributions extend beyond theoretical discussions, offering practical implications for enhancing data accessibility, semantic search, and automated knowledge discovery.

We are all beginning to appreciate how important #knowledgegraphs are to #RAG for robust #genAi apps. But did you know that KGs can make a significant improvement to #syntheticdata generation? Engineers need to generate synthetic technical data, particularly for industrial maintenance where real datasets (e.g. about failures) are often limited and unbalanced. This research offers a generic approach to extracting legitimate paths from a knowledge graph to ensure that synthetic maintenance/failure data generated are grounded in engineering knowledge while reflecting the style and language of the technicians who write the #maintenanceworkorders. Turing test experiments reveal that subject matter experts could distinguish real from synthetic data only 51% of the time while exhibiting near-zero agreement, indicating random guessing. Statistical hypothesis testing confirms the results from the Turing Test. Check out this paper which includes all code, data and documentation.  https://lnkd.in/gmyiJKtj Huge congrats to our amazing students who did this work Allison Lau and Jadeyn Feng Allison Lau Jadeyn Feng Caitlin Woods Michael Stewart, Tony Seale Vladimir Alexiev Sarah Lukens Tyler Bikaun, PhD Mark Warrener Piero Baraldi Caitlin Woods Milenija Stojkovic Helgesen MSHelgesen Nils Martin Rugsveen Chris McFarlane Jean-Charles Leclerc Adriano Polpo (de Campos) | 10 comments on LinkedIn

A bottom-up approach to knowledge graph development may be in part alike bottom-up ontology development from existing and legacy resources, but for sure also involves other tasks, and perhaps princ…

Table of Contents

I’ve tested countless Retrieval-Augmented Generation (RAG) systems, and they all failed to meet my expectations. I found a simple two-step…

If you’ve ever asked yourself, “Does GraphRAG really outperform vanilla RAG—and by how much?”, you’re not alone.

Welcome back, let’s dive into Chapter 50 of this insightful series!AI Exploration Journey is a reader-supported publication.