Yangtze River Delta Geographic Entity Categories

5.5 KB of data supports a framework achieving an F1 score of 0.898 for geographic entity recognition in the Yangtze River Delta river network. Zongjun Wei published this work in April 2026 to demonstrate automated knowledge graph construction.

Use Cases

• Training entity recognition models on categorized geographic entities from the Yangtze River Delta.
• Benchmarking relation extraction systems using the framework's reported 0.823 F1 score for spatial relationships.
• Validating geospatial knowledge graph construction methods against the multi-stage extraction strategy described.
• Analyzing river network structure using the categorized geographic entities and their relations.

Strengths

• Framework validated with an F1 score of 0.898 for entity recognition.
• Data is openly licensed under CC-BY-4.0 for reuse.

Limitations

• Dataset size is only 5.5 KB, indicating extremely limited scope or sample data.
• No column names, sample data, or row counts are provided for direct analysis.

Provenance

Source

Zongjun Wei via figshare.

Collection Method

Constructed via the LLM-Reflex-GeoKG framework for automated GeoKG building.

Freshness

Last updated in April 2026.

Geography

Yangtze River Delta river network.