Triple

T10140094
Position Surface form Disambiguated ID Type / Status
Subject Anne Kirrin E226957 entity
Predicate appearsWithCharacter P47747 FINISHED
Object George Kirrin E258599 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: George Kirrin | Statement: [Anne Kirrin, appearsWithCharacter, George Kirrin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Kirrin
Context triple: [Anne Kirrin, appearsWithCharacter, George Kirrin]
  • A. George Kirrin chosen
    George Kirrin is the adventurous, tomboyish girl from Enid Blyton’s Famous Five series who insists on being called “George” and often leads the group’s daring escapades.
  • B. Richard Hiscott
    Richard Hiscott is an editor known for his work on the television series "Willow."
  • C. George Drysdale
    George Drysdale was a 19th-century Scottish physician and early advocate of birth control and population reform, best known for his influential work "The Elements of Social Science."
  • D. John Kinley
    John Kinley is the central U.S. Army sergeant protagonist in Guy Ritchie's 2023 war film "The Covenant," known for his bond with an Afghan interpreter and his efforts to save him.
  • E. John Ferriter
    John Ferriter was an American television producer and talent agent known for his influential work in late-night TV and reality programming.
  • 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_69ca8433ec308190b8b25a6fe359c34c completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdeb2425008190a92c5148ed703d5c completed April 2, 2026, 4:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7947e14c88190b9e33e3fbdcc16e5 completed April 9, 2026, 11:58 a.m.
Created at: March 30, 2026, 9:07 p.m.