Early Modern GraphRAG: Knowledge Graph, Vector Index, and Evaluation Outputs
收藏Zenodo2026-05-28 更新2026-05-29 收录
下载链接:
https://zenodo.org/doi/10.5281/zenodo.20420920
下载链接
链接失效反馈官方服务:
资源简介:
The Chapter 3 GraphRAG knowledge graph (218,523 nodes / 691,577 edges) over an early modern British Atlantic corpus, with the chunk text and metadata for the vector collections emgraphrag_v2 and entity_evidence (embedding vectors not included; recomputable via the embedding pipeline), the Neo4j schema, a 10-document smoke test, and the full per-system LLM answers to the 30-question evaluation benchmark plus the 5 'ginger' case-study questions (including the Improved Scratchpad notes). Accompanies the Master's thesis Loud Yet Invisible: A Humanist-Designed Pipeline for Unlocking the Early Modern Archive (Jacob Polay, University of Saskatchewan, 2026). The graph and index include entities/relations extracted from EEBO-sourced OCR (extracted facts, not the page-scan text).
提供机构:
Zenodo创建时间:
2026-05-28



