Triple

T8207078
Position Surface form Disambiguated ID Type / Status
Subject American Madness E191713 entity
Predicate starredActor P5563 FINISHED
Object Kay Johnson E654653 NE FINISHED

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: Kay Johnson | Statement: [American Madness, starredActor, Kay Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kay Johnson
Context triple: [American Madness, starredActor, Kay Johnson]
  • A. Kay Johnson chosen
    Kay Johnson is the mother of American actor and activist James Cromwell.
  • B. Larkin Seiple
    Larkin Seiple is an American cinematographer known for his visually inventive work on films such as "Everything Everywhere All at Once."
  • C. Mo Johnston
    Mo Johnston is a former Scottish professional footballer and coach known for his prolific playing career as a striker and later managerial roles in Major League Soccer.
  • D. Jo Johnson
    Jo Johnson is a British Conservative politician and former Member of Parliament who has held ministerial roles, particularly in higher education and transport, and is the younger brother of former Prime Minister Boris Johnson.
  • E. Kay Bawden
    Kay Bawden is a social worker and one of the central adult characters in J.K. Rowling’s novel "The Casual Vacancy," whose professional and personal struggles highlight the book’s themes of class, responsibility, and community conflict.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82c7f3e08190857bf1fc63b2a10c completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb726b520081908ce4a03bd14dfcdf completed March 31, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd67dca77c8190bdae8a88648fc534 completed April 1, 2026, 6:45 p.m.
Created at: March 30, 2026, 5:43 p.m.