GraphRAG for the Chilean dictatorship: A knowledge graph approach to human rights archives

Archival research on human rights history records in Spanish, such as historical documents, faces the challenges of noisy Optical Character Recognition (OCR), fragmented testimony, and unstructured text that impede reliable retrieval. We implement GraphRAG, an automated framework that couples retrieval-augmented generation with knowledge graph construction to turn noisy corpora into interactive, verifiable network representations. To validate our proposed method, we apply GraphRAG to historical files on the assassination of Orlando Letelier, a well-known case. The pipeline cleans the OCR text, segments it, and extracts entities and relations under a bespoke ontology; it then performs entity resolution, full-text and vector indexing, community detection, and produces grounded summaries that cite explicit graph evidence. Across six retrieval strategies—vector search, a hybrid vector and keyword method, Cypher property queries, and entity-enhanced variants—we evaluate answers produced by GPT-4o mini and o3 mini against a historian-curated gold standard. The results show that Cypher queries that use properties dramatically reduce hallucinations, while hybrid methods improve recall, achieving 95% precision in a set of gold standard questions. Another case study on disappeared detained archives reveals dense personal and institutional hubs and illustrates GraphRAG's ability to reconcile conflicting testimony into coherent narratives. Our open-source framework offers a scalable blueprint for digital archives, museums, and human rights organizations, reshaping how societies preserve, interrogate, and govern historical data-intensive workflows.

Authors

Institutions

Publication Details

Journal
Big Data & Society
Published
2026-11-14
DOI
https://doi.org/10.1177/20539517261490265
Primary Topic
Digital Humanities and Scholarship
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

GraphRAG for the Chilean dictatorship: A knowledge graph approach to human rights archives

Hugo Rojas, Antonia Fonck Larraí­n, Domingo Mery, Jocelyn Dunstan et al.
Big Data & Society
Digital Humanities and Scholarship
article

GraphRAG for the Chilean dictatorship: A knowledge graph approach to human rights archives

Hugo Rojas, Antonia Fonck Larraí­n, Domingo Mery, Jocelyn Dunstan, Darwin Sanhueza
article en

Abstract

Archival research on human rights history records in Spanish, such as historical documents, faces the challenges of noisy Optical Character Recognition (OCR), fragmented testimony, and unstructured text that impede reliable retrieval. We implement GraphRAG, an automated framework that couples retrieval-augmented generation with knowledge graph construction to turn noisy corpora into interactive, verifiable network representations. To validate our proposed method, we apply GraphRAG to historical files on the assassination of Orlando Letelier, a well-known case. The pipeline cleans the OCR text, segments it, and extracts entities and relations under a bespoke ontology; it then performs entity resolution, full-text and vector indexing, community detection, and produces grounded summaries that cite explicit graph evidence. Across six retrieval strategies—vector search, a hybrid vector and keyword method, Cypher property queries, and entity-enhanced variants—we evaluate answers produced by GPT-4o mini and o3 mini against a historian-curated gold standard. The results show that Cypher queries that use properties dramatically reduce hallucinations, while hybrid methods improve recall, achieving 95% precision in a set of gold standard questions. Another case study on disappeared detained archives reveals dense personal and institutional hubs and illustrates GraphRAG's ability to reconcile conflicting testimony into coherent narratives. Our open-source framework offers a scalable blueprint for digital archives, museums, and human rights organizations, reshaping how societies preserve, interrogate, and govern historical data-intensive workflows.

Big Data & SocietyVol. 13(4)
Pontificia Universidad Católica de Chile (CL), Universidad Alberto Hurtado (CL), Universidad Católica del Uruguay (UY)
Digital Humanities and Scholarship
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon