Triple

T18949172
Position Surface form Disambiguated ID Type / Status
Subject Shenzhen University E463597 entity
Predicate hasLibrary P35 FINISHED
Object Shenzhen University Library NE NERFINISHED

How this triple was built (3 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Shenzhen University Library | Statement: [Shenzhen University, hasLibrary, Shenzhen University Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shenzhen University Library
Context triple: [Shenzhen University, hasLibrary, Shenzhen University Library]
  • A. Shenzhen Library
    Shenzhen Library is a major public library and cultural institution in Shenzhen, China, known for its extensive collections and modern architectural design.
  • B. Fudan University Library
    Fudan University Library is the main academic library system of Fudan University in Shanghai, China, providing extensive scholarly resources and research support to students and faculty.
  • C. Xiamen University Library
    Xiamen University Library is the main academic library system of Xiamen University in China, providing comprehensive research resources and study facilities for students and scholars.
  • D. Shenzhen University
    Shenzhen University is a comprehensive public university in Shenzhen, China, known for its rapid development, strong ties to the tech industry, and emphasis on innovation and applied research.
  • E. Peking University Library
    Peking University Library is one of China’s largest and most prestigious academic libraries, renowned for its extensive collections in the humanities, social sciences, and natural sciences.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shenzhen University Library
Target entity description: Shenzhen University Library is the main academic library of Shenzhen University, providing extensive print and digital resources, study spaces, and research support for students and faculty.
  • A. Shenzhen Library
    Shenzhen Library is a major public library and cultural institution in Shenzhen, China, known for its extensive collections and modern architectural design.
  • B. Fudan University Library
    Fudan University Library is the main academic library system of Fudan University in Shanghai, China, providing extensive scholarly resources and research support to students and faculty.
  • C. Xiamen University Library
    Xiamen University Library is the main academic library system of Xiamen University in China, providing comprehensive research resources and study facilities for students and scholars.
  • D. Shenzhen University
    Shenzhen University is a comprehensive public university in Shenzhen, China, known for its rapid development, strong ties to the tech industry, and emphasis on innovation and applied research.
  • E. Peking University Library
    Peking University Library is one of China’s largest and most prestigious academic libraries, renowned for its extensive collections in the humanities, social sciences, and natural sciences.
  • F. None of above. chosen

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d541ef18819080b2e253dd23835d completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, noon