ChronoGrapher: Event-centric Knowledge Graph Construction via Informed Graph Traversal

Event-centric knowledge graphs help enhance coherence to otherwise fragmented and overwhelming data by establishing causal and temporal connections using relevant data. We address the challenge of automatically constructing event-centric knowledge graphs from generic ones. We present ChronoGrapher, a two-step system to build an event-centric knowledge graph from grand events such as the French Revolution. First, an informed graph traversal retrieves connected sub-events from large, open-domain knowledge graphs. We define event-centric filters to prune the search space and a heuristic ranking to prioritise nodes like events. Second, we combine a rule-based system and information extraction from text to build event-centric knowledge graphs. ChronoGrapher demonstrates adaptability across datasets like DBpedia and Wikidata, outperforming approaches from the literature. To evaluate the utility of these graphs, we conduct a preliminary user study comparing different prompting techniques for event-centric question-answering. Our results demonstrate that prompts enriched with event-centric knowledge graph triples yield more factual answers compared to those enriched with generic knowledge graph triples or base prompts, achieving groundedness scores of 2.85, 2.24, and 1.11 respectively, while preserving succinctness and relevance.