Triple

T8385008
Position Surface form Disambiguated ID Type / Status
Subject Infernal Affairs E197793 entity
Predicate starring P1507 FINISHED
Object Andy Lau E467315 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: Andy Lau | Statement: [Infernal Affairs, starring, Andy Lau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Lau
Context triple: [Infernal Affairs, starring, Andy Lau]
  • A. Andy Lau chosen
    Andy Lau is a renowned Hong Kong actor and Cantopop singer, widely regarded as one of the most successful and influential stars in the Chinese entertainment industry.
  • B. Andrew Lau
    Andrew Lau is a Hong Kong filmmaker best known for co-directing the influential crime thriller "Infernal Affairs" and for his work on stylish action and triad films.
  • C. Zhang Hanyu
    Zhang Hanyu is a Chinese actor known for his powerful performances in films such as "Assembly" and "The Taking of Tiger Mountain."
  • D. Ringo Lam
    Ringo Lam was a renowned Hong Kong film director best known for his gritty, realistic crime thrillers such as "City on Fire," which heavily influenced the modern action and crime genre.
  • E. Chow Yun-fat
    Chow Yun-fat is a renowned Hong Kong actor celebrated for his charismatic performances in action and drama films such as "A Better Tomorrow" and "Crouching Tiger, Hidden Dragon."
  • 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80e03eb08190a458c9caa0524e0f completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce3967fd108190b045ea1328b1dc4b completed April 2, 2026, 9:39 a.m.
Created at: March 30, 2026, 6:02 p.m.