GraphNews

This blog post explores why building ontologies is essential yet notoriously difficult, and proposes a faster, more adaptive approach that bridges technical and domain expertise

Design infrastructure for a generative AI application with GraphRAG using Spanner Graph.

The open-source low-code platform releases version 5

Confession: until last week, I thought graphs were new. I shared what I thought was a fresh idea: that enterprise structured data should be modeled as a graph to make it digestible for today’s AI with its short context windows and text-based architecture. My post attracted graph leaders with roots in the Semantic Web. I learned that ontology was the big idea when the Semantic Web launched in 2001, and fell out of fashion by 2008. Then Google brought it back in 2012 —rebranded as the “knowledge graph” - and graphs became a mainstay in SEO. We’re living through the third wave of graphs, now driven by the need to feed data to AI agents. Graphs are indeed not new. But there’s no way I - or most enterprise data leaders of my generation - would have known that. I started my data career in 2013 - peak love for data lakes and disregard for schemas. I haven't met a single ontologist until 3 months ago (hi Madonnalisa C.!). And I deal with tables in the enterprise domain, not documents in public domain. These are two different worlds. Or are they?.. This 1999 quote from Tim Berners-Lee, the father of the Semantic Web hit me: “I have a dream for the Web [in which computers] become capable of analyzing all the data... When it [emerges], the day-to-day mechanisms of trade, bureaucracy, and our daily lives will be handled by machines talking to machines... The ‘intelligent agents’... will finally materialize.” We don't talk about this enough - but we are all one: ➡️ Semantic Web folks ➡️ Enterprise data teams ➡️ SEO and content teams ➡️ data providers like Scale AI and Surge AI In the grand scheme of things, we are all just feeding data into computers hoping to realize Tim’s dream. That’s when my initial shame turned into wonder. What if we all reimagined our jobs by learning from each other? What if enterprise data teams: ▶️ Prioritized algorithmic discoverability of their data assets, like SEOs do? ▶️ Pursued missing data that improves AI outcomes, like Scale AI does? ▶️ Took ownership of all data—not just the tables? Would we be the generation that finally realizes the dream? What a time to be alive. | 10 comments on LinkedIn

GraphDB's latest version powers enterprise AI with knowledge-grounded data, LLM integration, and scalable graph performance

How should we organize knowledge to provide the best context for agents? We show how knowledge graphs could play a key role in enhancing context for agents.

Watch how leading innovators are using graph technology to unlock complex data relationships and drive smarter decisions.

How Legal Documents and AI Reveal the Hidden Networks Behind Crime

Knowledge Graphs (KGs) are widely used in data-driven applications and downstream tasks, such as virtual assistants, recommendation systems, and semantic search. The accuracy of KGs directly...

How is fitness related to a bench? What is suitable for small spaces and can fit by both a sofa and a bed, serving as table but also being flexible to function as a bedside table? And what is a relevant product to complement a bed? Imagine all these questions answered by a furniture website. In one

Discover how Linkurious and Spanner Graph empower Google Cloud users with scalable, user-friendly graph analytics and visualization.

This study addresses the challenges of tracking and analyzing students' learning trajectories, particularly the issue of inadequate knowledge coverage in course assessments. Traditional assessment...

by Timothy Coleman A recent Guardian report drew attention to a key issue in the ride-hailing industry, spotlighting Uber’s use of sophisticated algorithms to enhance profits while prompting questions about clarity for drivers and passengers. Studies from Columbia Business School and the University

There’s a lot of buzz about #semanticlayers on LinkedIn these days. So what is a semantic layer? According to AtScale, “The semantic layer is a metadata and abstraction layer built on the source data (eg.. data warehouse, data lake, or data mart). The metadata is defined so that the data model gets enriched and becomes simple enough for the business user to understand.” It’s a metadata layer. Which can be taken a step further. A metadata layer is best implemented using metadata standards that support interoperability and extensibility. There are open standards such as Dublin Core Metadata Initiative and there are home-grown standards, established within organizations and domains. If you want to design and build semantic layers, build from metadata standards or build a metadata standard, according to #FAIR principles (findable, accessible, interoperable, reusable). Some interesting and BRILLIANT ✨folks to check out in the metadata domain space: Ole Olesen-Bagneux (O2)’s (check out his upcoming book about the #metagrid) Lisa N. Cao Robin Fay Jenna Jordan Larry Swanson Resources in comments 👇👇👇 | 29 comments on LinkedIn

How the idea of a semantic layer started, what are its elements, and how we can use it to enhance the performance of large language models

We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models to simultaneously...

In large Knowledge Graphs (KGs), measuring the importance of each entity is essential for improving search, navigation, and reasoning…

Forecasting is a fundamentally new capability that is missing from the current purview of generative AI. Here's how Kumo is changing that.

Uniquely Pioneering Graph Analytics Combined With Deep Search Galway, Ireland – 24th June, 2025 — Siren, the all-in-one investigation company, today announced its adoption of Graph Query Language (GQL), the world’s first ISO-standard query language for graphs, made public in 2024. With this move, Siren becomes the first investigative platform to offer seamless, standards-based graph … Continue reading "Siren Adopts ISO-Standard GQL to Power the Next Generation of Graph Intelligence"

After publishing my article on the Missing Semantic Center, a brilliant colleague asked me a question that gets to the heart of our technology stack: "But Tavi - this doesn't look like an OWL 2 DL ontology. What's going on here?" This question highlights a profound aspect of why systems have struggl

I've been working on autonomous AI systems, and wanted to share some thoughts on what I believe makes them effective. The challenge isn't just making AI that follows instructions well, but creating systems that can reason, and act independently.

🧠 When Is an Ontological Approach Not the Right Fit for Sharing and Reusing System Knowledge in Design and Development? Ontologies promise knowledge integration, traceability, reuse, and machine reasoning across the full engineering system lifecycle. From functional models to field failures, ontologies offer a way to encode and connect it all. 💥 However, ontologies are not a silver bullet. There are plenty of scenarios where an ontology is not just unnecessary, it might actually slow you down, confuse your team, or waste resources. So when exactly does the ontological approach become more burden than benefit? Based on my understanding and current work in this space, 🚀 For engineering design, it's important to recognise situations where adopting a semantic model is not the most effective approach: 1. When tasks are highly localised and routine If you're just tweaking part drawings, running standard FEA simulations, or updating well-established design details, then the knowledge already lives in your tools and practices. Adding an ontology might feel like installing a satellite dish to tune a local radio station. 2. When terminology is unstable or fragmented Ontologies depend on consistent language. If every department speaks its own dialect, and no one agrees on terms, you can't build shared meaning. You’ll end up formalising confusion instead of clarifying it. 3. When speed matters more than structure In prototyping labs, testing grounds, or urgent production lines, agility rules. Engineers solve problems fast, often through direct collaboration. Taking time to define formal semantics? Not always practical. Sometimes the best model is a whiteboard and a sharp marker. 4. When the knowledge won’t be reused Not all projects aim for longevity or cross-team learning. If you're building something once, for one purpose, with no intention of scaling or sharing, skip the ontology. It’s like building a library catalog for a single book. 5. When the infrastructure isn't there Ontological engineering isn’t magic. It needs tools, training, and people who understand the stack. If your team lacks the skills or platforms, even the best-designed ontology will gather dust in a forgotten folder. Use the Right Tool for the Real Problem Ontologies are powerful, but not sacred. They shine when you need to connect knowledge across domains, ensure long-term traceability, or enable intelligent automation. But they’re not a requirement for every task just because they’re clever. The real challenge is not whether to use ontologies, but knowing when they genuinely improve clarity, consistency, and collaboration, and when they just complicate the obvious. 🧠 Feedback and critique are welcome; this is a living conversation. Felician Campean #KnowledgeManagement #SystemsEngineering #Ontology #MBSE #DigitalEngineering #RiskAnalysis #AIinEngineering #OntologyEngineering #SemanticInteroperability #SystemReliability #FailureAnalysis #KnowledgeIntegration | 11 comments on LinkedIn

LLMs already contain overlapping world models. You just have to ask them right. Ontologists reply to an LLM output, “That’s not a real ontology—it’s not a formal conceptualization.” But that’s just the No True Scotsman fallacy dressed up in OWL. Boring. Not growth-oriented. Look forward, angel. A foundation model is a compression of human knowledge. The real problem isn't that we "lack a conceptualization". The real problem with an FM is that they contain too many. FMs contain conceptualizations—plural. Messy? Sure. But usable. At Stardog, we’re turning this latent structure into real ontologies using symbolic knowledge distillation. Prompt orchestration → structure extraction → formal encoding. OWL, SHACL, and friends. Shake till mixed. Rinse. Repeat. Secret sauce simmered and reduced. This isn't theoretical hard. We avoid that. It’s merely engineering hard. We LTF into that! But the payoff means bootstrapping rich, new ontologies at scale: faster, cheaper, with lineage. It's the intersection of FM latent space, formal ontology, and user intent expressed via CQs. We call it the Symbolic Latent Layer (SLL). Cute eh? The future of enterprise AI isn’t just documents. It’s distilling structured symbolic knowledge from LLMs and plugging it into agents, workflows, and reasoning engines. You don’t need a priesthood to get a formal ontology anymore. You need a good prompt and a smarter pipeline and the right EKG platform. There's a lot more to say about this so I said it at Stardog Labs https://lnkd.in/eY5Sibed | 17 comments on LinkedIn

Every year, businesses and consumers lose billions of dollars to fraud, with consumers reporting $12.5 billion lost to fraud in 2024, a 25% increase year over year. People who commit fraud often work together in organized fraud networks, running many different schemes that companies struggle to detect and stop. In this post, we discuss how to use Amazon Neptune Analytics, a memory-optimized graph database engine for analytics, and GraphStorm, a scalable open source graph machine learning (ML) library, to build a fraud analysis pipeline with AWS services.