GraphNews

A few weeks ago, Thomas Francart asked me what we put in OWL, what we put in SHACL, and what our rule of thumb is to decide. I wrote this post to answer these…

Author: Nicolas Figay Status: DraftAuthor: Nicolas Figay Status: Draft Last update: 2025-01-14 This article was initiated due to the success of the following post A post being not enough for addressing the topic, here is the article developing the subject deeper. Introduction When diving into the wo

Graph contrastive learning (GCL) is a self-supervised learning technique for graphs that focuses on learning representations by contrasting different views of…

As technology advances, large language models (LLMs) and information retrieval/management methods evolve at breakneck speed. Knowledge…

Graph Retrieval Augmented Generation (Graph RAG) is emerging as a powerful addition to traditional vector search retrieval methods. Graphs are great at repre...

A RAG System Built for Both Semantic Search and Structured Data Queries

Ashley Faith hosted Amy Hodler and me on a recent episode about “2025 Predictions” — here are notes I prepared, to review in 2026…

The SEMIC Style Guide for Semantic Engineers provides guidelines for developing and reusing semantic data specifications, particularly eGovernment Core…

LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.

This paper presents OG-RAG, an Ontology-Grounded Retrieval Augmented Generation method designed to enhance LLM-generated responses by anchoring retrieval processes in domain-specific ontologies....

While retrieval-augmented generation is effective for simpler queries, advanced reasoning questions require deeper connections between information that exist across documents. They require a knowledge graph.

Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is...

Exploring OWL Ontologies Visually: A Paradigm Shift in Understanding 🌐 In the world of semantic web 🌐 and ontology modeling, inverse properties are a… | 24 comments on LinkedIn

What are the key components of an ontology? Ontologies can seem a bit abstract at first, but when you break them down into their core components, they become… | 21 comments on LinkedIn

Create Cypher queries with an easy-to-use drag-and-drop interface

Stop struggling with Cypher syntax Turn graph queries into drag-and-drop Moving from SQL to Cypher presents a common challenge. You understand how data… | 54 comments on LinkedIn

Learn why enterprise graph initiatives often fail, early warning signs to watch for, and how to ensure success in unlocking connected organizational knowledge.

At the top of my list of New Year’s resolutions this year is relation resolution. In the world of structured knowledge, relations can make or break a project and mean the difference between infinite maintenance and long-term value.

A Semantic Model of the GDPR Register of Processing Activities This presentation explains the development of a consolidated data model for GDPR compliance…

How is an ontology different from a schema? At first glance, ontologies and schemas might seem similar, they both organize and define data. But the… | 54 comments on LinkedIn

Background: The field of Artificial Intelligence has undergone cyclical periods of growth and decline, known as AI summers and winters. Currently, we are in the third AI summer, characterized by...

Did you know that Knowledge Graphs are the silent backbone powering AI agents like chatbots and search engines? The path to this innovation wasn’t… | 36 comments on LinkedIn

Even after 50 years, Structured Query Language, or SQL, remains the native tongue for those who speak data. It's had impressive staying power since it was first coined the Structured Query English Language in the mid-1970s. It's survived and thrived through the dot-com era and the proliferation of cloud technology. In essence, SQL is a technology that evolves.

The Evolution of Intelligent Recommendations with Agentic Graph Systems ➿ Agentic graph systems for recommendation represent a sophisticated fusion of…

Exploring OWL Ontologies Visually: A Paradigm Shift in Understanding 🌐 When diving into the world of Web Ontologies (OWL), it's easy to get caught up in…

🚀 Breaking Boundaries in Graph + Retrieval-Augmented Generation (RAG)! 🌐🤖 The rapid pace of innovation in combining graphs with RAG is absolutely…

Amazon’s AGI Information is seeking an exceptional Senior Ontologist to drive ontology advancements. The team is innovating to optimize knowledge graph ontology for LLM understanding.We're looking for a Sr Ontologist to join us in sunny Santa Barbara and help us build this future. As a member of the team, you will have the opportunity to work on interesting cutting edge problems with immediate customer impact. Your initial focus will be on developing LLM friendly ontologies and you will have the opportunity to work with product managers, engineers, and scientists to develop tools to help on this endeavor. A successful candidate has a strong background with building knowledge systems to deliver world-class, intuitive, and comprehensive taxonomy and ontology models, a proven track record of innovation to adapt to the new work of LLM, and experience with leading a team of ontologists.As a Senior Ontologist, you will leverage your technical expertise and experience to demonstrate leadership in modeling large complex knowledge systems. Your first responsibility will be to structure a team of ontologists to deliver LLM friendly ontology for tens of verticals to feed the Amazon Knowledge Graph with trustworthy, live-updating, high-quality, and accurate structured information about all entities and data of interest to our customers. You will define roadmaps and goals to make progress incrementally and you will insist on delivering results leading by example.Key job responsibilities- Develop logical, semantically rich, and extensible data models for Amazon's extensive product catalog- Ensure our ontologies provide comprehensive domain coverage that are available for both human and machine ingestion and inference- Create new schema using Generative Artificial Intelligence (generative AI) models- Analyze website metrics and product discovery behaviors to make data-driven decisions on optimizing our knowledge graph data models globally- Expand and refine the expansion of data retrieval techniques to utilize our extensive knowledge graph- Contribute to team goal setting and future state vision- Drive and coordinate cross-functional projects with a broad range of merchandisers, engineers, designers, and other groups that may include architecting new data solutions- Develop team operational excellence programs, data quality initiatives and process simplifications- Evangelize ontology and semantic technologies within and across teams at Amazon- Mentor and influence peers

Copyright 2025 Kurt Cagle/The Cagle Report In my last post, I talked about ontologies as language toolkits, but I'm going to take a somewhat different tack with this piece: exploring the relationship between and ontology and a knowledge graph. Ontologies = Schemas + Taxonomies Let me repeat my opera

We contributed recently to the "awesome semantic shapes" repository. This is a community-curated list of RDF shape resources, be it validators, generators…