Triple

T16525969
Position Surface form Disambiguated ID Type / Status
Subject Norman Colin Dexter E401437 entity
Predicate spouse P13 FINISHED
Object Dorothy Cooper 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: Dorothy Cooper | Statement: [Norman Colin Dexter, spouse, Dorothy Cooper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dorothy Cooper
Context triple: [Norman Colin Dexter, spouse, Dorothy Cooper]
  • A. Dorothy Cooper chosen
    Dorothy Cooper was the wife of British crime writer Colin Dexter, known for supporting him throughout his career creating the Inspector Morse novels.
  • B. Dorothy Cooper
    Dorothy Cooper was an American screenwriter active during Hollywood's mid-20th century studio era, contributing scripts to several feature films.
  • C. Dorothy DuBois
    Dorothy DuBois was the wife of American Treasury Department lawyer and Holocaust whistleblower Josiah E. DuBois Jr.
  • D. Dorothy Adams
    Dorothy Adams was an American character actress known for her numerous supporting roles in Hollywood films from the 1930s through the 1950s.
  • E. Dorothy Bussy
    Dorothy Bussy was an English novelist and translator best known for her close association with French writer André Gide and for translating many of his works into English.
  • 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32ed3f0388190a9f03473c37dfc46 completed April 18, 2026, 7:12 a.m.
Created at: April 10, 2026, 5:14 a.m.