GraphNews

How an ontology-based knowledge graph boosts the multi-hop Q&A accuracy of one of the leading schemaless GraphRAG systems

Trust has stood out more than ever in the light of recent innovations. Some examples are advances in artificial intelligence that make machines more and more humanlike, and the introduction of...

I ran 30 context experiments to understand which piece of context has the most impact on analytics agents performance

A Graph Practitioner’s Perspective

From Property Graphs to OWL Inference Using a Hybrid Pipeline

Here is a very simple example of graph with AGE PostgreSQL extension. In this example, we will assume we are trying to match a donor who can potentially donate to a patient based on the matching blood group.

Why copying data for graph analytics doesn’t scale, and what you can do instead

2025 was a big year for Spanner on Google Cloud, with new capabilities to help it evolve from a passive data repository to an intelligent context hub.

The integration patterns that make LLMs more reliable and controllable

AI agents act under your authority. If you can’t trace their reasoning or enforce boundaries, you don’t have governance. You have risk. Here’s the evidence.

Misinformation spreads quickly—but fact-checking can happen just as fast.

High-performance GraphRAG inspired from LightRag written in Rust - raphaelmansuy/edgequake

Part 2 — Generative Knowledge Operators

How Terminology Pollution Is Killing Graph Architecture And Where GraphQL Actually Belongs

Thursday was eventful - I had 37 phone calls from recruiters looking for ontologists. One of them sent a questionnaire that I thought was brilliant, and I am reproducing here, because if you are an ontologist, you should probably be able to address these issues: 1. Have you designed or implemented a Knowledge Graph in an enterprise environment? (Yes + can describe use case = proceed) 2. Which semantic technologies have you worked with hands-on (RDF, OWL, SPARQL, SHACL)? (Should name at least 2 confidently) 3. Was your work more architecture-focused, hands-on, or hybrid? (Looking for senior ownership) Semantic Depth 4. Have you designed or managed ontologies or semantic models tied to business domains? 5. How did your Knowledge Graph integrate with relational or warehouse data? AI / RAG / KAG Exposure 6. Have you worked on platforms supporting LLMs, RAG, or AI systems using enterprise data? 7. Do you understand the difference between RAG and Knowledge-Augmented Generation (KAG)? (Conceptual understanding is acceptable) 8. Have you integrated Knowledge Graphs with embeddings or vector search? Enterprise & Governance 9. How did governance, lineage, or trust factor into your semantic or AI architecture? 10. Have you worked in regulated or large enterprise environments? Platform Alignment 11. What cloud platforms have you worked on? Any hands-on GCP data services? 12. Have you embedded semantic logic into data pipelines or ingestion flows? Seniority & Communication 13. Have you defined standards or reference architectures used by multiple teams? 14. How do you explain Knowledge Graphs to business stakeholders? | 42 comments on LinkedIn

Discover some of the best technical talks and videos from the NODES 2025 online conference organized by Neo4j and curated by Christian Miles from G.V().

The context graph will be the single most valuable asset for companies building and deploying AI systems.

Decision traces aren't enough for agent memory. Learn how world models and behavioral validation create AI that predicts outcomes. Build smarter agents.

Watching the Grok situation unfold has felt strangely familiar.

Coming Soon: [KNOWLEDGE GRAPH] 1 Industry, 5 Million+ Queries Problem 1: How do I learn ALL the topics in my industry? Solution: Structure 5.3M raw queries into a 5-level taxonomy → Categories → Subcategories → Intents → Topics → Keywords Problem 2: How do I use this data? Solution:  → Visualize & filter topics at scale → Track rankings vs competitors → Calculate market share % by topic Problem 3: How does this drive business impact? [Coming Soon] Solution: → Increase topical coverage with intent-based content → 3-4 year content & optimization roadmap → Internal linking recommendation engine Current Scale: • 5,331,768 keywords indexed • 913 L1 categories • 746 L2 subcategories   • 882 L3 intents • 1ms classification speed Productivity Impact: Manual: 1,000 keywords = 2 hours This system: 5.3M keywords = instant Select the topics YOU care about → Find opportunities → Start IMPLEMENTING #KnowledgeGraph #SEO #DataEngineering #Telecom #AI | 83 comments on LinkedIn

Building a Knowledge Graph Is Hard.

You may have come across many #GraphRAG articles on how to go about building knowledge graphs — the patterns, the frameworks, the debates…

GLiNER2 extracts structured data without the LLM tax.

Was recently notified of MD-LD https://mdld.js.org/, a Markdown linked data parser in Javascript, that enables to create structured data while authoring MD. Same idea as RDFa for HTML, but in Markdown. It builds on my original blog post "semantic markdown" from 2020 : https://lnkd.in/ejwRqa5x So you write thinks like "## Meeting notes {=ex:Meeting_1 .schema:Event}" The very cool (and impressive) thing is the roundtrip : after the parser has extracted triples, and you modify the triples, you can regenerate the markdown file with updated structured annotations. Imagine : a lightweight solution to mix content-written-for-the-web with structured data. And could ask your AI to enrich your markdown with this syntax. And the structured data lives inside the content. And you can query your journal / notes / task lists in SPARQL. A pretty cool solution for personal knowledge graphs, or larger ones. This opens a whole new world of possibilities.

💻 Your website might be clear to you, but search engines and AI systems form their own interpretation. In the course AI Search and LLMs Entity SEO and Knowledge Graph Strategies for Brands for MLforSEO , I walk through how to verify what Google and AI models actually understand about your content. The analysis is based on Google Natural Language API and Knowledge Graph Search API, focusing on entity recognition and salience signals that influence AI citations and semantic visibility. If your brand or product is not clearly identified as a primary entity, your content is harder to surface in AI driven search experiences. This course explains how to test, diagnose, and correct that. 👉 The course is published at the following link and goes into the methodology step by step: https://lnkd.in/dvFiM8ct