GraphNews

LLM have fundamentally changed how we interact with data , automate reasoning and build intelligent systems .However , despite their…

There’s a recurring tension in how people talk about the semantic spectrum and especially ontologies. On one side, ontology is treated as the peak.

Foundation Capital's piece on Context Graphs as AI's next trillion-dollar opportunity is making the rounds.

Can you explain what is your function and where it fits in the overall drug development and commercialization process? I am a director of data at BMS and I work with translational data. This includes areas such as translational safety, translational medicine, and reverse translation.

AIM MarketView: Graph Databases 2026 is now live 🔴 Graph databases are rapidly emerging as core platforms for relationship-centric analytics, knowledge graphs, and agentic AI–enabled decision systems. The AIM MarketView: Graph Databases 2026 provides a comprehensive view of the global graph database ecosystem, profiling 30 leading vendors and analyzing how platforms are evolving across scale, intelligence, and enterprise adoption. 🔍 What’s inside the report: - Landscape of 30 graph database vendors spanning property graph, RDF/semantic, multimodel, cloud-native, and open-source architectures - Vendor-specific use cases and commercial models for every profiled graph DB/platform. - Deep dive into Graph + AI convergence, including GraphRAG, vector–graph integration, and graph-based reasoning - Adoption insights across financial services, cybersecurity, life sciences, telecom, retail, manufacturing, and the public sector As enterprises move beyond isolated analytics toward context-aware, connected intelligence, graph databases are becoming foundational to both AI-native architectures and agentic systems. Aerospike | Altair | Amazon | Arango | BangDB | FalkorDB | Fluree | Franz Inc. | Google | Graphwise | HugeGraph | Hypermode | InfiniteGraph | JanusGraph | Microsoft Azure | Memgraph | Neo4j | NebulaGraph, powered by Vesoft | OrientDB | Oracle | Oxford Semantic Technologies (RDFox) | Progress MarkLogic - Progress Data Platform | Rocketgraph | Sparsity Technologies (Sparksee) | Stardog | TerminusDB | TigerGraph | Ultipa #VelocityGraph #GraphDatabases #KnowledgeGraphs #DataEngineering #AgenticAI #GraphRAG #AIMMarketView #AIM

Why Decision-Aware AI Requires Managed Meaning, Not Just Memory

We all feel overwhelmed by information. Data everywhere. Connecting the dots feels impossible. Unstructured, messy data will never power truly smart AI. But there is a solution: structuring knowledge into graphs. 🚀 Introducing 𝘗𝘦𝘳𝘴𝘦𝘶𝘴, a Text-to-Graph SDK by Lettria. Automatically build tailor-made Knowledge Graphs and GraphRAG pipelines in minutes. ➡️ +𝟰𝟱% 𝗶𝗺𝗽𝗿𝗼𝘃𝗲𝗱 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 on average compared to traditional RAG. Why Perseus? 1️⃣ Super simple to use: Ingest PDF ⇒ convert to .md/.txt ⇒ generate a .ttl knowledge graph ⇒ accurate retrieval. 2️⃣ Edge reliability: Domain-and business specific automatic graph building. No illogical links, no weird nodes. Just clean communities and relationships. 3️⃣ Ontology guided (optional): Bring your own ontology (or use one of Lettria's) to guide the graph building with your custom logic. What you can build: 🔗 GraphRAG pipelines 🧠 AI agent persistent memory 🤖 Multi-agent systems 📊 Analytics & BI Example: python pdf_to_markdown.py mydoc. pdf python index.py mydoc. md python report. py"What are the main topics?" ✅ Coding agents: Claude Code, Cursor, Codex compatible. ✅ Export to Graph DBs: Neo4j native integration. ✅ Compatible with AWS Neptune, Ultipa, TigerGraph, ArangoDB, JanusGraph. 👉 We're opening Premium Early Access for a few weeks. Install the package from GitHub: https://lnkd.in/dKbWV429 🔑 Get your API key from the Perseus web app 👥 Join our Graph Discord community (links in the comments).

🧠 Context graphs are increasingly discussed as a foundational layer for agentic systems—framed by Jaya Gupta and Ashu Garg as a “trillion-dollar opportunity”—but their real value lies in preserving decision context.

Context Graphs and Process Knowledge, It's The Same Thing

Some thoughts on the latest buzzwords

Free, open-source RDF & ontology visualization tools 👇

Building a self-improving knowledge graph that doesn’t just store data, it understands, validates, and evolves it

The idea of decision traces and context graphs is exciting for a very specific reason: for the first time, we have a plausible way to learn the behavior of an ontology.

Knowledge Graphs vs Context Graphs: Maps vs GPS

Amazing news, guys.

Ontologies are knowledge artifacts 🧠 , but they’re also software artifacts 💻 .

Context graphs exploded in January 2026.

Part 2 of from Data Engineering to Knowledge Engineering

The SPARQL query language is the standard method to access knowledge graphs (KGs). However, formulating SPARQL queries is a significant challenge for non-expert users, and remains time-consuming for the experienced ones. Best practices recommend to document KGs with competency questions and example queries to contextualise the knowledge they contain and illustrate their potential applications. In practice, however, this is either not the case or the examples are provided in limited numbers. Large Language Models (LLMs) are being used in conversational agents and are proving to be an attractive solution with a wide range of applications, from simple question-answering about common knowledge to generating code in a targeted programming language. However, training and testing these models to produce high quality SPARQL queries from natural language questions requires substantial datasets of question-query pairs. In this paper, we present Q²Forge that addresses the challenge of generating new competency questions for a KG and corresponding SPARQL queries. It iteratively validates those queries with human feedback and LLM as a judge. Q²Forge is open source, generic, extensible and modular, meaning that the different modules of the application (CQ generation, query generation and query refinement) can be used separately, as an integrated pipeline, or replaced by alternative services. The result is a complete pipeline from competency question formulation to query evaluation, supporting the creation of reference query sets for any target KG.

Combining IT Infrastructure, Service, and Security Operations Data for Real Insights

A pragmatic approach to interoperability: model your data richly for your own needs, then allow the eventual creation of one‑to‑many alignments.

A personal note on AI music fatigue, distrust of rec engines, and using Wikidata queries to browse like a record store.

Learn how JanusGraph with Azure Managed Cassandra enables scalable, high-performance graph applications for complex relationship analysis.

Clustering, Cognition, and Ontology Engineering: The Proven Foundations We’re witnessing a powerful convergence in modern knowledge engineering. At its heart lies a decades-old pairing: the TBox-ABox architecture of description logics. This split between a schema layer (TBox: classes, axioms, rules) and an assertional layer (ABox: instances, facts) is more than a modeling convenience—it is the structural backbone for scalable, interpretable, and efficient knowledge systems.​ 1. Bidirectional TBox-ABox Reasoning: The TBox-ABox relationship isn’t just a one-way street. Modern ontology platforms implement feedback cycles—TBox-driven reasoning enriches ABox data, while patterns discovered in ABox instances suggest new or improved TBox axioms. Automated systems like DL-Learner and AMIE+ exemplify this virtuous loop, blending logical inference with machine-driven discovery.​ 2. Iterative Refinement and Machine Learning Analogies: While not mathematically identical, the iterative cycles in clustering algorithms (such as EM or K-Means) echo the knowledge-refinement process in ontologies. In one, the cluster centroids and assignments are repeatedly updated to improve fit. In the other, TBox rules and ABox facts are successively refined for logical coherence and empirical richness. This analogy, though conceptual, powerfully illustrates the self-improving nature of mature knowledge systems.​ 3. Horn Logic for Computational Efficiency: Horn logic unlocks polynomial-time reasoning, the foundation of OWL 2 RL and similar profiles. By restricting to Horn clauses, systems achieve tractable, scalable inferences that keep production-grade knowledge graphs accurate and responsive—even at enterprise scale.​ 4. DL Safety and Rule Guarantees: Combining rules (SWRL) with expressive ontologies (OWL DL) is notoriously tricky—adding rules risks undecidability. The DL-Safety condition was a breakthrough, enforcing restrictions that ensure automated reasoning stays sound and terminates, without sacrificing the power of rule-based schema enrichment.​ 5. Dual Validation for Trustworthy Knowledge: Ontology-based data access (OBDA) completes the story by empirically grounding logic-driven schemas in live production data, while reasoners like HermiT enforce logical consistency. This dual validation ensures that knowledge systems are both scientifically sound and operationally reliable.​ Key Takeaway: Today’s most robust knowledge systems don’t rely on black-box heuristics or wishful analogies. Their power comes from rigorous, validated architectures: bidirectional ontology refinement, tractable logic fragments, and principled integration of logical and statistical learning. This is the true engine behind scalable, explainable, and trustworthy enterprise AI. #OntologyEngineering #KnowledgeGraphs #MachineLearning #SemanticWeb

Understanding Failure Scenarios from LLM-based Entity & Relationship Extraction

This codelab teaches you how to build intelligent multi-agent systems using Google’s Agent Development Kit (ADK) combined with Neo4j graph databases and the Model Context Protocol (MCP) Toolbox. You’ll learn to create specialized GraphRAG-powered agents that leverage knowledge graphs for context-aware query responses, implement agent orchestration patterns, and deploy pre-validated database queries as reusable tools. By the end, you’ll have built a production-ready investment research system demonstrating best practices for next-generation retrieval agents.