Structured knowledge representation of the South China Sea: An LLM-based knowledge graph approach
Ruinan Zhao, Zhifan Han, Huiling Liu · 2026
Read Structured knowledge representation of the South China Sea: An LLM-based knowledge graph approach by Ruinan Zhao, Zhifan Han, Huiling Liu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351132.txt.
Description
South China Sea knowledge lies scattered across many sources. Historical, legal, and political texts span centuries. Ruinan Zhao, Zhifan Han, and Huiling Liu used a large language model to join them. They built a knowledge graph from the sources. A knowledge graph stores facts as linked triples. Computers can search and reason over it.
The pipeline works in three stages. It extracts facts, standardizes names, and verifies links. The finished graph holds nearly sixty thousand entities. It stores over six hundred fifty thousand fact triples. Users can answer questions across eras. Hidden multi-step connections also surface. The authors offer the method for other tangled domains.
Catalog record
| CREATOR | Ruinan Zhao, Zhifan Han, Huiling Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66683 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |