Triple

T8842347
Position Surface form Disambiguated ID Type / Status
Subject 19 E210416 entity
Predicate singleFromAlbum P1995 FINISHED
Object Cold Shoulder E761006 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: Cold Shoulder | Statement: [19, singleFromAlbum, Cold Shoulder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cold Shoulder
Context triple: [19, singleFromAlbum, Cold Shoulder]
  • A. Cold Shoulder chosen
    Cold Shoulder is a fashion style or garment design characterized by cut-out sections at the shoulders, leaving them exposed while the rest of the sleeve remains intact.
  • B. Cold Hearted
    "Cold Hearted" is a hit 1989 dance-pop single by American singer Paula Abdul, noted for its edgy choreography and prominent MTV music video.
  • C. Cold Hearted
    "Cold Hearted" is a track from the 1982 hard rock album *Corridors of Power* by Northern Irish guitarist Gary Moore.
  • D. Cold as Ice
    "Cold as Ice" is a 1977 rock song by the British-American band Foreigner, known for its catchy piano riff and themes of emotional detachment in a romantic relationship.
  • E. Love's Cruelty
    Love's Cruelty is a Caroline-era tragic play by James Shirley that explores themes of passion, betrayal, and moral corruption in a courtly setting.
  • 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_69ca838967bc8190b46c3c80a2887ea4 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc608946cc8190bed3c340ba303b9c completed April 1, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfa0721430819091abe8c13a745725 completed April 3, 2026, 11:11 a.m.
Created at: March 30, 2026, 6:48 p.m.