Triple

T20746294
Position Surface form Disambiguated ID Type / Status
Subject Bruce Clark E510591 entity
Predicate sharesSurnameWith P13741 FINISHED
Object Petula Clark 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: Petula Clark | Statement: [Bruce Clark, sharesSurnameWith, Petula Clark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petula Clark
Context triple: [Bruce Clark, sharesSurnameWith, Petula Clark]
  • A. Petula Clark chosen
    Petula Clark is a British singer and actress best known for her 1960s pop hits like "Downtown" and her successful film and stage career.
  • B. Cilla Black
    Cilla Black was a popular English singer and television presenter who rose to fame in the 1960s with hit singles and later became a beloved UK TV personality.
  • C. Barbara Whiteman
    Barbara Whiteman is a wealthy, neurotic Beverly Hills housewife whose life is upended by a homeless man in the comedy film "Down and Out in Beverly Hills."
  • D. Barbara Whiteman
    Barbara Whiteman is known as the wife of Dave Whiteman.
  • E. Sandy Shaw
    Sandy Shaw is a screenwriter best known for co-writing the 1988 action thriller film "The Dead Pool" in the Dirty Harry series.
  • 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_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c225c564819088f2461467698095 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:33 p.m.