Triple

T14486807
Position Surface form Disambiguated ID Type / Status
Subject Prince of Yan E359249 entity
Predicate regionAssociated P21614 FINISHED
Object Yan E827545 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: Yan | Statement: [Prince of Yan, regionAssociated, Yan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yan
Context triple: [Prince of Yan, regionAssociated, Yan]
  • A. Yan
    Yan is a Chinese surname historically borne by various notable figures and families across different regions of China.
  • B. Yan chosen
    Yan was an ancient Chinese state during the Zhou dynasty era, located in the northeast and later annexed by the expanding Qin state in the late 3rd century BCE.
  • C. Yun
    Yun is the Chinese given name of Jack Ma, the billionaire co-founder and former executive chairman of Alibaba Group.
  • D. Yun
    Yun is a Korean family name borne by numerous historical figures, politicians, and cultural personalities in Korea.
  • E. Yanaoca
    Yanaoca is a small Andean town in southern Peru that serves as the administrative and commercial center of Canas Province in the Cusco Region.
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de924ee0f08190baf68318b41fa64d completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd64a925148190992101984895a20b completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:20 a.m.