Automatic knowledge-graph creation from historical documents: The Chilean dictatorship as a case study

TL;DR

This paper demonstrates an approach to automatically construct a knowledge graph from historical documents about the Chilean dictatorship using large language models, with grounding in an ontology to reduce hallucinations.

Contribution

It introduces a method combining LLMs and a simple ontology for entity and relation recognition in historical texts, improving knowledge graph accuracy.

Findings

Recognized a significant portion of entities in the gold standard graph.

Most unrecognized entities are due to granularity issues, not model misses.

The approach shows promise for humanities and social science research.

Abstract

We present our results regarding the automatic construction of a knowledge graph from historical documents related to the Chilean dictatorship period (1973-1990). Our approach consists on using LLMs to automatically recognize entities and relations between these entities, and also to perform resolution between these sets of values. In order to prevent hallucination, the interaction with the LLM is grounded in a simple ontology with 4 types of entities and 7 types of relations. To evaluate our architecture, we use a gold standard graph constructed using a small subset of the documents, and compare this to the graph obtained from our approach when processing the same set of documents. Results show that the automatic construction manages to recognize a good portion of all the entities in the gold standard, and that those not recognized are mostly explained by the level of granularity in which the information is structured in the graph, and not because the automatic approach misses an important entity in the graph. Looking forward, we expect this report will encourage work on other similar projects focused on enhancing research in humanities and social science, but we remark that better evaluation metrics are needed in order to accurately fine-tune these types of architectures.