Triple

T17024296
Position Surface form Disambiguated ID Type / Status
Subject Police Story E413023 entity
Predicate cinematographyBy P1953 FINISHED
Object Cheung Yiu-jo
Cheung Yiu-jo is a cinematographer best known for his work on the influential Hong Kong action film "Police Story."
E1252678 NE FINISHED

How this triple was built (4 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: Cheung Yiu-jo | Statement: [Police Story, cinematographyBy, Cheung Yiu-jo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cheung Yiu-jo
Context triple: [Police Story, cinematographyBy, Cheung Yiu-jo]
  • A. Chow Kwok-hung
    Chow Kwok-hung is a Hong Kong politician known for his involvement in local governance and public affairs.
  • B. Chow Kwok-yan
    Chow Kwok-yan is a person notable enough to be specifically distinguished among individuals with the surname Chow.
  • C. Chow Kwok-lun
    Chow Kwok-lun is an individual notable enough to be specifically cited as a bearer of the surname Chow, though detailed public information about his life or achievements is limited.
  • D. Chan Kwong-wing
    Chan Kwong-wing is a Hong Kong film composer best known for his scores for acclaimed movies such as the Infernal Affairs trilogy.
  • E. Chow Kwok-keung
    Chow Kwok-keung is a notable individual who bears the surname Chow, recognized for his distinct contributions or public presence associated with that family name.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cheung Yiu-jo
Triple: [Police Story, cinematographyBy, Cheung Yiu-jo]
Generated description
Cheung Yiu-jo is a cinematographer best known for his work on the influential Hong Kong action film "Police Story."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cheung Yiu-jo
Target entity description: Cheung Yiu-jo is a cinematographer best known for his work on the influential Hong Kong action film "Police Story."
  • A. Chow Kwok-hung
    Chow Kwok-hung is a Hong Kong politician known for his involvement in local governance and public affairs.
  • B. Chow Kwok-yan
    Chow Kwok-yan is a person notable enough to be specifically distinguished among individuals with the surname Chow.
  • C. Chow Kwok-lun
    Chow Kwok-lun is an individual notable enough to be specifically cited as a bearer of the surname Chow, though detailed public information about his life or achievements is limited.
  • D. Chan Kwong-wing
    Chan Kwong-wing is a Hong Kong film composer best known for his scores for acclaimed movies such as the Infernal Affairs trilogy.
  • E. Chow Kwok-keung
    Chow Kwok-keung is a notable individual who bears the surname Chow, recognized for his distinct contributions or public presence associated with that family name.
  • F. None of above. chosen

Provenance (5 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d371148190a60d32a72abec09a completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01413cc6f08190ae83a0c98fb96b90 completed May 11, 2026, 2:38 a.m.
NEDg Description generation batch_6a014218d0cc81909c1b1b4c11484364 completed May 11, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_6a01427ce5d08190b383ea907ca3352e completed May 11, 2026, 2:44 a.m.
Created at: April 10, 2026, 5:33 a.m.