The Procedural Knowledge Ontology, From Theory to Practice

In this episode of Founders Discussion, TuringDB founders Adam Amara and Rémy Boutonnet sit down to discuss one of the most important and often overlooked ca...

Stop overloading your contexts!

SEOs have been mildly obsessed with knowledge graphs for a while, but mostly because we want to ensure that our websites/brands/clients are well represented in Google’s Knowledge Graph, which makes sense. What not many of us have had experience with (myself included) is building our own knowledge graphs. It is technically challenging and not immediately apparent what the benefit is, and some people aren’t aware that it isn't exclusive to Google. Pioneers like Andrea Volpini and Dixon Jones have long been advocates for approaching this in a more nuanced way. Right now, I’m just learning in public, so stick with me. So what have I learned? - Structured data is IMPORTANT. Not just schema, but having tried to reliably infer semantic triples across a 1000+ document set using an LLM, it’s clear that easily understable/scrapable data is KEY - As a second point, I might not recommend doing this with an LLM at all… depends on your objective (more below). But using a merchant feed (for example) OR schema and graphing that would ultimately be easier. - It’s too easy to forget to provide explicit context for key information. For example, when you strip a page down to JUST its readable content, does it still make sense? Maybe the key question here is, “Why build yourself a knowledge graph, though?” It’s an excellent opportunity to learn, but also quite a painful experience - especially when each full processing run has taken about 18 hours, so you need a good reason. Here are my goals: - Searchable knowledge store/database, particularly looking for “facts”, great for content writing - Trying to document the knowledge an LLM can easily infer by way of a basic simulation of how other models may understand content. Not in a reverse-engineering sense, but to really highlight what information IS NOT clear/specific - A grounded knowledge store for LLM content generation - rather than a model making up key details, we can use this KG as a store of already signed-off details. Creating a basic API for Cursor/Claude Code to use as a Tool is where I am starting This is not an “are you even an SEO if you’re not building knowledge graphs in 2026” post - that would be madness. This process is challenging and clearly not worthwhile for many, many people. But if you have large-scale content challenges and want a really in-depth way to understand them, I can totally see the value. If this isn’t you, but you want to benefit from some elements of this, I’d probably ask Dixon about Waiky 😉 | 15 comments on LinkedIn

Recent discussions around platform consolidation, real-time data pipelines, and AI architecture increasingly emphasize the strategic role of formal semantics. The argument is compelling: as cloud providers, streaming platforms, and AI stacks become vertically integrated, enterprises risk losing not

Hybrid RAG combines vector search with knowledge graphs to fix retrieval blind spots, boost support accuracy, and cut investigation time in enterprise systems.

There has always been a fundamental problem with SPARQL: you need to understand the data model to use it.

Evaluating LLM Prompts for Entity & Relation Extraction, and Why Complexity Never Disappears

A sneak peak into the constraint language.

Join Hannah Bast and myself on Friday 12 December at 10am Eastern / 4pm CET to discuss “Benchmarking of Triple Stores and SPARQL engines” at https://lnkd.in/eEJr69zu

I got my new LLM entity resolution system working great!

Introduction: Why Your Knowledge Graph Strategy Needs Multiple Ingestion Techniques

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We...

Knowledge Graphs shouldn't require a PhD

An Overview on Graph Types for Graph RAG: Structures, Schemas, and When to Use Each One

Huge news for Cosmograph 🪐 While everyone was on Thanksgiving break, I was polishing up the next big Cosmograph update, which I'm finally ready to share! More than three years after the initial release, Cosmograph remains the only single-node web-based tool capable of visualizing graphs with 1 million points and way more than a million links due to its unique GPU Force Layout and Rendering engine cosmos.gl. However, it also had a few major weaknesses like poor memory management and limited analytical capabilities. Version 2.0 of Cosmograph solves these problems by incorporating: - DuckDB (the best in-memory analytics database); - Mosaic (the fastest cross-filtering and visual analytics framework for the web); - SQLRooms (an open-source React toolkit for human and agent collaborative analytics apps by Ilya Boyandin) as its foundation; - The latest version of cosmos.gl (our core force simulation and rendering engine that recently joined OpenJS) to give you even faster performance, more forces, and the long-awaited point-dragging functionality! What does this mean in practice? - Work with larger datasets and use SQL (thanks to WebAssembly and DuckDB); - Much better performance (filtering, timeline, changing visual properties of the graph, etc.); - Open Parquet files natively; - Save your graphs to the cloud and share them with the world easily. And if you work with ML embeddings and love Apple's Embedding Atlas (https://lnkd.in/gsWt6CNT), you'll love Cosmograph too since they have a lot in common. If all the above has excited you, go check out Cosmograph's new beautiful website, and share the news with the world 🙏 https://cosmograph.app | 41 comments on LinkedIn

LPG is NOT a hypergraph

OSMnx is a Python package that downloads any city’s street network, buildings, bike lanes, rail, or walkable paths from OpenStreetMap and instantly turns them into clean, routable NetworkX graphs with correct topology, projected coordinates, edge lengths, bearings, and travel speeds.

Zero-config Python graph database with process isolation and Unix socket communication. Build graph apps instantly without Docker or port management.

Scientific Reports - Research on the construction and application of retrieval enhanced generation (RAG) model based on knowledge graph

Ontology vs. Conceptual Data Modeling, Implementation of Semantic Foundations, and Using Agents in the Right Places for Enrichment

I'm excited to announce that DeepGraph AI is open-sourcing GraphLite—the first fully open-source embedded graph database implementing the ISO GQL standard (ISO/IEC 39075:2024) in Rust.

Your AI agents can't reason about what they can't structurally represent.

Inside LinkedIn’s AI ‘cookbook’: How engineers scaled GenAI to 1.3B users by distilling models to 220M parameters for a 10x throughput gain.

Most agentic systems hardcode their capabilities.