Triple

T17749459
Position Surface form Disambiguated ID Type / Status
Subject Curse of the Golden Flower E443074 entity
Predicate producer P490 FINISHED
Object Zhang Weiping 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: Zhang Weiping | Statement: [Curse of the Golden Flower, producer, Zhang Weiping]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zhang Weiping
Context triple: [Curse of the Golden Flower, producer, Zhang Weiping]
  • A. Zhang Weiping chosen
    Zhang Weiping is a Chinese film producer best known for his long-time collaboration with director Zhang Yimou on several internationally acclaimed movies.
  • B. Zhou Weiping
    Zhou Weiping is a film producer best known for producing the acclaimed Chinese movie "Red Sorghum."
  • C. Zhang Heping
    Zhang Heping is a Chinese theatre and film producer best known for his key role in organizing and overseeing major cultural events, including the 2008 Beijing Olympics ceremonies.
  • D. Zhao Jiping
    Zhao Jiping is a renowned Chinese composer best known for his evocative film scores for directors like Zhang Yimou and Chen Kaige.
  • E. Zhou Jingzhi
    Zhou Jingzhi is a Chinese screenwriter best known for co-writing the historical drama film "Curse of the Golden Flower" directed by Zhang Yimou.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48418c0188190beb31809b40e4648 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.