Triple

T15358474
Position Surface form Disambiguated ID Type / Status
Subject Bullet Train (film score) E367223 entity
Predicate composedForCharacter P30143 FINISHED
Object Tangerine (Bullet Train character)
Tangerine is a sharp-tongued, stylish British assassin and one half of the “Twins” duo in the action-comedy film Bullet Train.
 E1153187 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: Tangerine (Bullet Train character) | Statement: [Bullet Train (film score), composedForCharacter, Tangerine (Bullet Train character)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tangerine (Bullet Train character)
Context triple: [Bullet Train (film score), composedForCharacter, Tangerine (Bullet Train character)]
  • A. Mr. Nice
    Mr. Nice is a 2010 biographical crime film in which Rhys Ifans portrays real-life Welsh drug smuggler Howard Marks.
  • B. Tucci
    Tucci is the surname of Stanley Tucci, an acclaimed American actor, writer, director, and producer known for his versatile roles in film and television.
  • C. Figan
    Figan is an individual known primarily through their familial relationship as the child of Flo.
  • D. Tapper
    Tapper is a surname most notably associated with English actress Zoe Tapper.
  • E. Jett
    Jett is a neo-noir crime drama television series starring Carla Gugino as a world-class thief navigating dangerous criminal underworlds after her release from prison.
  • 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: Tangerine (Bullet Train character)
Triple: [Bullet Train (film score), composedForCharacter, Tangerine (Bullet Train character)]
Generated description
Tangerine is a sharp-tongued, stylish British assassin and one half of the “Twins” duo in the action-comedy film Bullet Train.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tangerine (Bullet Train character)
Target entity description: Tangerine is a sharp-tongued, stylish British assassin and one half of the “Twins” duo in the action-comedy film Bullet Train.
  • A. Mr. Nice
    Mr. Nice is a 2010 biographical crime film in which Rhys Ifans portrays real-life Welsh drug smuggler Howard Marks.
  • B. Tucci
    Tucci is the surname of Stanley Tucci, an acclaimed American actor, writer, director, and producer known for his versatile roles in film and television.
  • C. Figan
    Figan is an individual known primarily through their familial relationship as the child of Flo.
  • D. Tapper
    Tapper is a surname most notably associated with English actress Zoe Tapper.
  • E. Jett
    Jett is a neo-noir crime drama television series starring Carla Gugino as a world-class thief navigating dangerous criminal underworlds after her release from prison.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e2d4934819097fc63603964217c completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b47f20081909ef7b077458d1510 completed May 9, 2026, 10:24 a.m.
NEDg Description generation batch_69ff0dde2ec48190aac70b0513fb1847 completed May 9, 2026, 10:35 a.m.
NED2 Entity disambiguation (via description) batch_69ff0e5eabf08190811d8a91bfe0de76 completed May 9, 2026, 10:37 a.m.
Created at: April 10, 2026, 3:18 a.m.