Triple

T1150530
Position Surface form Disambiguated ID Type / Status
Subject Zooropa E23665 entity
Predicate recordLabel P1500 FINISHED
Object PolyGram E106922 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: PolyGram | Statement: [Zooropa, recordLabel, PolyGram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PolyGram
Context triple: [Zooropa, recordLabel, PolyGram]
  • A. PolyGram chosen
    PolyGram was a major international music entertainment company and record label group, particularly influential in the late 20th century.
  • B. Astralwerks
    Astralwerks is an American record label known for releasing influential electronic and dance music from prominent artists and producers.
  • C. NPG Records
    NPG Records is an independent record label founded by Prince, known for releasing his music and that of associated artists.
  • D. Erato Records
    Erato Records is a French classical music record label renowned for its high-quality recordings and strong focus on Baroque and early music repertoire.
  • E. Elektra Music Group
    Elektra Music Group is a major American record label and music company known for signing and promoting a diverse roster of contemporary artists across multiple genres.
  • 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_69a493f0d32c8190ac74bad3c87f2641 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc730b008190bd0901e0a47a4b7a completed March 1, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5eb5d36c8190916a43a5f41df144 completed March 7, 2026, 5:21 p.m.
Created at: March 1, 2026, 7:44 p.m.