Triple

T12348415
Position Surface form Disambiguated ID Type / Status
Subject Kamikaze E294416 entity
Predicate includesSingle P11236 FINISHED
Object So Sexy E977239 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: So Sexy | Statement: [Kamikaze, includesSingle, So Sexy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: So Sexy
Context triple: [Kamikaze, includesSingle, So Sexy]
  • A. So Sexy chosen
    "So Sexy" is a track by the French rapper Kamikaze, known within his discography for its slick, street-influenced style and catchy, modern production.
  • B. I’m Too Sexy
    "I'm Too Sexy" is a 1991 novelty dance-pop song by British duo Right Said Fred, known for its humorous, self-parodying lyrics about extreme vanity.
  • C. You Sexy Thing
    "You Sexy Thing" is a 1975 disco and funk hit song by the British band Hot Chocolate, fronted by singer-songwriter Errol Brown, that became one of their most enduring and recognizable tracks.
  • D. Sexy 17
    Sexy 17 is a track from David Guetta’s debut album "Just a Little More Love," known for its club-oriented electronic dance style.
  • E. Sexy Bitch
    "Sexy Bitch" is a 2009 electro-house and dance-pop single by French DJ David Guetta featuring Akon that became a global club hit and chart success.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f7ba17481908b03af7316b28d9b completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6346dd09481908f4c80e89e2f4705 completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:53 p.m.