Triple

T17453736
Position Surface form Disambiguated ID Type / Status
Subject Zwan E424979 entity
Predicate hasMember P10 FINISHED
Object Billy Corgan 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: Billy Corgan | Statement: [Zwan, hasMember, Billy Corgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Billy Corgan
Context triple: [Zwan, hasMember, Billy Corgan]
  • A. Billy Corgan chosen
    Billy Corgan is an American musician, best known as the frontman and primary songwriter of the alternative rock band The Smashing Pumpkins.
  • B. Jeremy Enigk
    Jeremy Enigk is an American singer-songwriter best known as the frontman of the influential indie rock band Sunny Day Real Estate and for his atmospheric solo work.
  • C. Matt Sharp
    Matt Sharp is an American musician best known as the original bassist for Weezer and the founder of the band The Rentals.
  • D. Brian "Head" Welch
    Brian "Head" Welch is an American guitarist and songwriter best known as a founding member and lead guitarist of the nu metal band Korn.
  • E. Mark Arm
    Mark Arm is an American musician best known as the frontman of the influential grunge band Mudhoney and a key figure in the Seattle grunge scene.
  • 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_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451406c748190b5ac6aacff7a3cc7 completed April 19, 2026, 3:51 a.m.
Created at: April 10, 2026, 5:47 a.m.