Triple

T21994481
Position Surface form Disambiguated ID Type / Status
Subject Last Midnight E543169 entity
Predicate originalPerformer P11499 FINISHED
Object Bernadette Peters 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: Bernadette Peters | Statement: [Last Midnight, originalPerformer, Bernadette Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernadette Peters
Context triple: [Last Midnight, originalPerformer, Bernadette Peters]
  • A. Bernadette Peters chosen
    Bernadette Peters is a celebrated American actress and singer, renowned for her work in musical theatre, film, and television, particularly in numerous Stephen Sondheim productions.
  • B. Kelli O'Hara
    Kelli O'Hara is a Tony Award–winning American actress and soprano best known for her leading roles in Broadway musicals and revivals.
  • C. Patricia Denner Cayne
    Patricia Denner Cayne is best known as the wife of James Cayne, the former CEO and chairman of Bear Stearns.
  • D. Melba Moore
    Melba Moore is an American singer and actress known for her powerful vocals and Tony Award–winning work on Broadway as well as her success in R&B music.
  • E. Patti LuPone
    Patti LuPone is a celebrated American stage and screen actress and singer, renowned for her powerful voice and iconic performances in major Broadway musicals.
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:18 p.m.