Triple

T16016817
Position Surface form Disambiguated ID Type / Status
Subject 21 Questions E388487 entity
Predicate producer P490 FINISHED
Object Dirty Swift E755485 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: Dirty Swift | Statement: [21 Questions, producer, Dirty Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dirty Swift
Context triple: [21 Questions, producer, Dirty Swift]
  • A. Dirty Swift chosen
    Dirty Swift is a music producer best known as one half of the American production duo MIDI Mafia, recognized for their work in hip-hop and R&B.
  • B. Dirty Love
    "Dirty Love" is a collection of interconnected novellas by American author Andre Dubus III that explores the complexities of desire, betrayal, and emotional vulnerability in contemporary relationships.
  • C. Damn Right
    "Damn Right" is a dancehall/reggae album by Jamaican artist Mr. Vegas, showcasing his energetic vocal style and party-ready tracks.
  • D. Wild at Heart
    Wild at Heart is a 1990 surreal crime-romance film directed by David Lynch, known for its violent, dreamlike road-movie style and starring Nicolas Cage and Laura Dern.
  • E. Wild at Heart
    Wild at Heart is a British television drama series set in South Africa that follows a veterinary surgeon and his family as they run a wildlife game reserve.
  • 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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18295c6a4819093263db8669d4b08 completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf2a4b0c819094f629c65cf8f880 completed May 10, 2026, 12:19 a.m.
Created at: April 10, 2026, 4:55 a.m.