Triple

T20573707
Position Surface form Disambiguated ID Type / Status
Subject Hitman 2 (2018) E505160 entity
Predicate series P1761 FINISHED
Object Hitman 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: Hitman | Statement: [Hitman 2 (2018), series, Hitman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hitman
Context triple: [Hitman 2 (2018), series, Hitman]
  • A. Hitman
    Hitman is a 1998 Filipino action film starring Cesar Montano as a professional assassin entangled in crime and moral conflict.
  • B. Hitman chosen
    Hitman is a 2007 action film adaptation of the video game series, featuring a genetically engineered assassin known as Agent 47.
  • C. The Hitman
    The Hitman is the ring nickname of Thomas Hearns, the legendary American professional boxer known for his devastating punching power and multiple world titles across different weight classes.
  • D. Hitman: Agent 47
    Hitman: Agent 47 is a 2015 action film adaptation of the Hitman video game series, centered on a genetically engineered assassin known only by his barcode tattoo and codename, Agent 47.
  • E. The Hitman’s Bodyguard
    The Hitman’s Bodyguard is a 2017 action-comedy film starring Ryan Reynolds and Samuel L. Jackson, known for its blend of high-octane stunts and irreverent humor.
  • 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_69e0b4b721588190993ac7b0a9be2736 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a9087af88190a4610ecb29f637ca completed April 20, 2026, 10:30 p.m.
Created at: April 16, 2026, 11:39 a.m.