Work

Silo to Structure – A Pipeline for Extracting Knowledge Graphs from Historical Sources with LLMs

Year: 2025

Type: article

Abstract: We introduce a computational pipeline that transforms heterogeneous historical sources into knowledge graphs using large language models (LLMs). It combines LLM-based open information extraction (OIE) with competency-question-guided ontology building and is grounded in three principles: task decomposition, human-in-the-loop validation, and research-question- and data-driven design.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17292799

Authors: Schlattmann, Raphael, Kaye, Aleksandra, Vogl, Malte

Institutions: Technische Universität Berlin, Max Planck Institute of Geoanthropology, Max Planck Institute for the History of Science

Language: English

Topic: Digital Humanities and Scholarship

Subfield: Literature and Literary Theory

Field: Arts and Humanities

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W7085750045

FWCI:

Cites:

Cited by:

Related to: