GraphNews

Palantir built a $400B empire on ontology-first AI systems long before LLMs.

🗂️⚠️ Much of the current conversation around AI focuses on bias, ethics, and governance — but rarely does it dig into the history of categories themselves and their lasting impact.

A nod to a storytelling genius in the Age of SHACL

How reifications shape the way we think about data.

Decompose large PRs into a DAG of small, reviewable stacked PRs - vitali87/pr-split

"We'll Just Get an LLM to Write Our Ontology"

Part 3 — Evaluation Framework

Table of Contents

Bridging Wikidata, MeSH, and DO in a Unified Knowledge Graph

Turn your scattered AI coding sessions into a queryable knowledge graph. Multi-platform (Claude Code, ChatGPT, DeepSeek, Grok, Warp), W3C ontology, Wikidata entity linking, SPARQL. - robertoshimizu...

LinkedIn is walking through a massive people graph — but smartly.

We finished the first half of "GraphRAG: The Definitive Guide" with O'Reilly and have it available for early access today. We now cover everything from Knowledge Graph Concepts to Common GraphRAG Patterns. This is a great reference on GraphRAG for anyone who wants to incorporate graphs into their Agentic Application! 🤖📔🎉 https://lnkd.in/gMSp8VGh

To understand how to answer world questions from data models, we don't need semantic layers, we need ontologies

I turned the Ramayana into a structured Knowledge Graph and built a Agentic Graph RAG system on top of it.

#SkillsOnTheRise Ontologists and taxonomists - people who deal with data models, and how they drive both traditional and artificial intelligence systems, will be some of the most in-demand professions in 2026. Most large language models (LLMs) are trained on web content, and the very thing that gives them their incredible fluency also makes them unreliable with data, especially data that isn't already in their systems (which can include most of the data that is likely of value to your organisation). To increase reliability and reduce hallucinations, one emerging need is to "ground" this data, provide content that is both specific to your company's needs while at the same time ensuring that the data that is produced remains consistent and follows a specific structure. This is the area where ontologists come in. Ontologists are information architects who focus on what things are relevant to you, how those things relate to one another, and how information can be extracted from this data in a flexible, timely, and consistent manner. This data is usually stored in #knowledge_graphs, huge interconnected data structures that provide encyclopedic information, or in #context_graphs, similar systems designed to record information in terms of events and history. #Ontologies provide the rules that define these structures. #Ontologists provide structure and design at the outset, making data systems (and not just AI systems) much more stable, predictable, and reliable. They are likely to be indispensible to businesses in the next few years.

CosmosAIGraph implementation of OmniRAG pattern. Contribute to AzureCosmosDB/CosmosAIGraph development by creating an account on GitHub.

Live from San FranciscoThis inaugural Context Graph Meetup in San Francisco brings together researchers, engineers, and early adopters exploring context grap...

Sharing datasets that change (through creates, updates, deletes) poses challenges to data consumers, including reconciling historical versioning and managing fr...

Ontology Pipeline as a strategic framework for semantic engineers to prove their professional value by linking abstract models to functional entity resolution

BigQuery Graph Series | Part 3: Query and Visualize your Graph Welcome to Part 3 of our series! In Part 2, we built a BigQuery Graph from unstructured data. Now, it’s time to query and visualize …

BigQuery Graph Series | Part 2: (Tutorial) Build a BigQuery Graph from unstructured data In Part 1, we explored how to unlock unstructured “dark data” by using a Hybrid AI approach — pairing …

Introducing SurrealDB 3.0 - the future of AI agent memory

PageRank surfaces what actually matters in your network. It identifies the most influential nodes based not just on how many connections they have, but on the quality of those connections. Whether you’re pinpointing critical suppliers, high-value customers, emerging fraud hubs,… Read more →