Triple

T21492418
Position Surface form Disambiguated ID Type / Status
Subject Charles Durning E530269 entity
Predicate spouse P13 FINISHED
Object Carole Doughty 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: Carole Doughty | Statement: [Charles Durning, spouse, Carole Doughty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carole Doughty
Context triple: [Charles Durning, spouse, Carole Doughty]
  • A. Carole Doughty chosen
    Carole Doughty is known as the first wife of American character actor Charles Durning.
  • B. Pauline Carr
    Pauline Carr is an Australian business leader and governance professional who serves as the chancellor of the University of South Australia.
  • C. Doreen Brett
    Doreen Brett was the wife of British comedian and actor Norman Wisdom.
  • D. Joyce Grange
    Joyce Grange is a local community center in Joyce, Washington that serves as a gathering place for social, recreational, and civic activities.
  • E. Mary Hartnett
    Mary Hartnett is an American lawyer and author best known as a co-author of the definitive biography of U.S. Supreme Court Justice Ruth Bader Ginsburg.
  • 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_69e0c45bd15481909fba5910765cdda2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea54fb608190a147cd8aa6d6d04b completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:23 p.m.