Triple

T8170194
Position Surface form Disambiguated ID Type / Status
Subject Liuyang E190796 entity
Predicate provinceCapitalOfJurisdiction P42013 FINISHED
Object Changsha E29743 NE FINISHED

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: Changsha | Statement: [Liuyang, provinceCapitalOfJurisdiction, Changsha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Changsha
Context triple: [Liuyang, provinceCapitalOfJurisdiction, Changsha]
  • A. Changsha chosen
    Changsha is the capital city of Hunan Province in south-central China, known as a historic cultural center and major regional economic hub.
  • B. Zhuzhou
    Zhuzhou is a major industrial and transportation hub city in south-central China, known especially for its rail transit and manufacturing industries.
  • C. Changde
    Changde is a city in northwestern Hunan Province, China, historically significant as a major battleground during the Second Sino-Japanese War.
  • D. Xiangtan
    Xiangtan is a prefecture-level city in central Hunan Province, China, known as an important industrial and commercial hub and for encompassing Shaoshan, the birthplace of Mao Zedong.
  • E. Hengyang
    Hengyang is a major industrial and transportation hub city in southern China, located along the Xiang River in the south of Hunan Province.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: provinceCapitalOfJurisdiction
Context triple: [Liuyang, provinceCapitalOfJurisdiction, Changsha]
  • A. regionCapital
    Indicates that one entity is the capital city or administrative center of a specified region.
  • B. governsCapital
    Indicates that a political authority or administrative body exercises governing control over a capital city.
  • C. territoryCapital
    Indicates that one entity is the capital city or administrative center of a specified territory.
  • D. governingStateCapital
    Indicates that a state serves as the governing political authority over the specified capital city.
  • E. capitalCityOfJurisdiction chosen
    Indicates that one entity is the primary city serving as the official capital of the specified jurisdiction or governing region.
  • F. None of above.

Provenance (4 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_69ca82c1c0a08190bf8692b4d91a03ca completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4803de688190960438aa059d163b completed March 31, 2026, 4:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cced5a4398819085364b3a45a85941 completed April 1, 2026, 10:03 a.m.
PD Predicate disambiguation batch_69cb36a4c40c81909f60aef0e1624c13 completed March 31, 2026, 2:51 a.m.
Created at: March 30, 2026, 5:39 p.m.