Context Graphs: Evolving Beyond Knowledge Graphs for Adaptive Intelligent Systems

Knowledge graphs have become the standard way to encode structured facts about a domain: entities, their attributes, and the relationships between them. They answer the question "what is true?" remarkably well. Yet as software systems become more autonomous—driven by large language models, agents, and continuous streams of organisational activity—a different question dominates: "what is true right now, for this user, in this situation, and why?"

This white paper introduces and formalises the context graph, a graph structure that extends the knowledge graph with four additional dimensions: time, provenance, situational scope, and decision traces. It presents the conceptual model, a reference architecture for building context graphs from live operational data, a systematic comparison with classical knowledge graphs, practical applications (retrieval-augmented generation, proactive enterprise agents, compliance and audit, personalisation), a pragmatic construction methodology, and open challenges around decay, privacy, and scale.