Knowledge graphs and ontologies are frequently proposed as essential components of GraphRAG architectures for grounding large language models, improving retrieval, and providing a semantic layer. However, discussions of these concepts often remain informal, with terms such as context, semantic layer, and even knowledge graph used without precise definitions. This ambiguity makes it difficult to compare approaches, evaluate implementations, or reason about their capabilities.

Your chance to visit the exhibits and network with fellow attendees.

Semantics in the Age of AI: Questions Practitioners Must Answer in 2026

Context and challenge

As AI systems become the primary way people and applications access information, the semantic layer (ontologies, knowledge graphs, and contextual metadata) has moved from nice‑to‑have to critical infrastructure. Yet many organisations still struggle to decide when to invest in graphs, how to manage change, and how to align semantic work with data and AI teams.

Meeting the challenge

Join our speakers to explore the ideas, insights and provocations from the morning’s sessions.

Over the past three years, the AI conversation has evolved from Generative AI to AI-ready data, and now to agentic AI and autonomous business. Yet one fundamental truth has remained constant: AI is only as effective as the data that grounds it.

As organizations move beyond chatbots to intelligent agents capable of orchestrating business processes, the need for well-organized, well-described enterprise data has never been greater.

Early Lessons from a Work in Progress

The Challenge

Your chance to visit the exhibits and network with fellow attendees.

Organizations are increasingly evaluating large language models (LLMs) for content classification and tagging. While LLMs offer flexibility and can accelerate semantic model development, they also introduce considerations around consistency, explainability, governance, and cost.