Triple

T17069884
Position Surface form Disambiguated ID Type / Status
Subject Mulan (2020 film) E414187 entity
Predicate portrayedBy P1507 FINISHED
Object Liu Yifei E1157472 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: Liu Yifei | Statement: [Mulan (2020 film), portrayedBy, Liu Yifei]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liu Yifei
Context triple: [Mulan (2020 film), portrayedBy, Liu Yifei]
  • A. Liu Yifei chosen
    Liu Yifei is a Chinese-American actress, singer, and model best known internationally for starring as the title character in Disney’s live-action film "Mulan."
  • B. Jiang Yili
    Jiang Yili was a Qing dynasty official who served as a high-ranking regional administrator and military commander in southern China.
  • C. Chen Yifei
    Chen Yifei was a prominent Chinese painter and film director known for his romantic realist style and influential role in modern Chinese art.
  • D. Zhou Dongyu
    Zhou Dongyu is a prominent Chinese actress acclaimed for her versatile performances in films such as "Under the Hawthorn Tree" and "Soul Mate," for which she has received multiple major acting awards.
  • E. Wang Ziyi
    Wang Ziyi is an actor known for his role in the Hong Kong workplace musical comedy-drama film "Office" (2015), directed by Johnnie To.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbbfb1f08190807301ff6e573cf5 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0139f5d34081908bd9e88fb5772ddc completed May 11, 2026, 2:07 a.m.
Created at: April 10, 2026, 5:34 a.m.