Triple

T19713985
Position Surface form Disambiguated ID Type / Status
Subject Soochow University E473425 entity
Predicate nativeName P15 FINISHED
Object 苏州大学 NE NERFINISHED

How this triple was built (2 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: 苏州大学 | Statement: [Soochow University, nativeName, 苏州大学]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 苏州大学
Context triple: [Soochow University, nativeName, 苏州大学]
  • A. Soochow University chosen
    Soochow University is a major comprehensive research university in Suzhou, China, known for its strong programs in humanities, social sciences, and engineering.
  • B. 西南大学
    西南大学 is a comprehensive national university in Chongqing, China, known for its strengths in teacher education, agriculture, and the humanities and social sciences.
  • C. 南开大学
    南开大学 is a prestigious comprehensive research university in Tianjin, China, renowned for its strong academic tradition and influential alumni.
  • D. Yangzhou University
    Yangzhou University is a comprehensive public university in Yangzhou, Jiangsu Province, China, known for its strengths in agriculture, engineering, and teacher education.
  • E. Nanjing Normal University
    Nanjing Normal University is a comprehensive public university in Nanjing, China, known for its strong teacher education programs and broad range of disciplines.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6440b47508190a8a33325b00841dc completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.