Triple

T15660756
Position Surface form Disambiguated ID Type / Status
Subject Taipei City Council E376559 entity
Predicate nativeName P15 FINISHED
Object 台北市議會 E77408 NE FINISHED

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: 台北市議會 | Statement: [Taipei City Council, nativeName, 台北市議會]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 台北市議會
Context triple: [Taipei City Council, nativeName, 台北市議會]
  • A. Taipei City Council chosen
    The Taipei City Council is the elected municipal legislative body responsible for enacting local laws, budgets, and oversight for Taiwan’s capital city.
  • B. New Taipei City Council
    The New Taipei City Council is the elected municipal legislature responsible for making local laws, budgets, and policies for New Taipei City in Taiwan.
  • C. Taipei City Government
    The Taipei City Government is the municipal authority responsible for administering and providing public services for Taiwan’s capital city, Taipei.
  • D. New Taipei City Government
    New Taipei City Government is the municipal authority responsible for administering and providing public services for New Taipei City, Taiwan’s most populous municipality.
  • E. 臺北市
    臺北市是臺灣的首都與最大都會區之一，為國家的政治、經濟、文化與交通中心。
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef4e6a08190ad8bbafaa3612f22 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ed6f50c81909d87ced263064f0d completed May 9, 2026, 5:28 p.m.
Created at: April 10, 2026, 4:15 a.m.