Triple

T8066537
Position Surface form Disambiguated ID Type / Status
Subject Wu Zixu E188256 entity
Predicate helpedConquer P33868 FINISHED
Object Ying, capital of Chu E704505 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: Ying, capital of Chu | Statement: [Wu Zixu, helpedConquer, Ying, capital of Chu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ying, capital of Chu
Context triple: [Wu Zixu, helpedConquer, Ying, capital of Chu]
  • A. Ying (later Chu capital) chosen
    Ying was the later capital city of the ancient Chinese state of Chu, serving as its major political and cultural center.
  • B. Jianye
    Jianye is an ancient name for the city now known as Nanjing, a historically significant capital in several Chinese dynasties.
  • C. Yuncheng
    Yuncheng is a major city in southern Shanxi Province, China, known for its historical sites and role as a regional transportation and economic hub.
  • D. Licheng
    Licheng is the courtesy name of the Daoguang Emperor, a Qing dynasty ruler of China in the early 19th century.
  • E. Qujing
    Qujing is a major prefecture-level city in eastern Yunnan Province, China, known as an important regional transportation and industrial hub.
  • 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: helpedConquer
Context triple: [Wu Zixu, helpedConquer, Ying, capital of Chu]
  • A. conqueredIn
    Indicates that one entity gained control over another entity or territory as a result of a specific conquest event or campaign.
  • B. conqueredThroughGeneral
    Indicates that one entity achieved conquest or control over another entity by means of a specific general who led or directed the successful military action.
  • C. wasAssistedBy
    Indicates that an entity carried out an action or achieved a result with the help or support of another entity.
  • D. helpedEscape
    Indicates that one entity assisted another in getting away from confinement, danger, or pursuit.
  • E. helpedCause chosen
    Indicates that one entity contributed to bringing about, enabling, or facilitating an outcome or event involving another entity.
  • 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_69ca82b42674819086840efea12478e5 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3ff75d208190b7c53d2fe55878ac completed March 31, 2026, 3:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63e1ed44819083ed9db6c9d7b0fd completed April 1, 2026, 12:16 a.m.
PD Predicate disambiguation batch_69cb049cd51c8190bb3b0f503e42fa8d completed March 30, 2026, 11:17 p.m.
Created at: March 30, 2026, 5:26 p.m.