Yangtze River Delta Geographic Entity and Relation Dataset

A 9.5 KB Excel file containing non-spatial relations and definitions for constructing a Geographic Knowledge Graph (GeoKG). The dataset was created by researcher Zongjun Wei and published on figshare in April 2026. It supports a framework for automated knowledge extraction from river network data.

Use Cases

• Train or evaluate models for geographic entity recognition using the defined entity types from the Yangtze River Delta.
• Benchmark relation extraction systems against the non-spatial relations defined in this dataset.
• Validate the LLM-Reflex-GeoKG framework's output for constructing domain-specific knowledge graphs.
• Use the structured definitions as a reference for annotating river network and watershed management data.

Strengths

• Dataset is associated with a framework achieving an F1 score of 0.898 on geographic entity recognition.
• Dataset is associated with a framework achieving an F1 score of 0.823 on relation extraction.
• Published under a permissive CC-BY-4.0 license for open use.

Limitations

• Very small dataset at only 9.5 KB, indicating limited scope and sample size.
• Specific row count, column names, and data structure within the Excel file are unknown.
• Geographic coverage is limited to the Yangtze River Delta river network.

Provenance

Source

Zongjun Wei via figshare.

Collection Method

Created as part of a research study proposing the LLM-Reflex-GeoKG framework for automated GeoKG construction.

Freshness

Last updated in April 2026.

Geography

Yangtze River Delta river network.