Triple

T19954393
Position Surface form Disambiguated ID Type / Status
Subject Sir John Kirk E479644 entity
Predicate name P16 FINISHED
Object John Kirk 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: John Kirk | Statement: [Sir John Kirk, name, John Kirk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Kirk
Context triple: [Sir John Kirk, name, John Kirk]
  • A. John Kirk chosen
    John Kirk is a relatively common personal name shared by multiple individuals across various professions and historical periods.
  • B. John Kirkpatrick
    John Kirkpatrick is an English folk musician and singer renowned for his virtuoso playing of the melodeon, button accordion, and concertina, and for his influential role in the British folk revival.
  • C. George Daniel Weaver
    George Daniel Weaver, better known as Buck Weaver, was an American third baseman for the Chicago White Sox and one of the players banned from Major League Baseball for life following the 1919 Black Sox scandal.
  • D. Charles Irwin
    Charles Irwin was the husband of American actress Helen Mack, known primarily in relation to her career in early 20th-century film and radio.
  • E. Thomas Kirk
    Thomas Kirk was a 19th-century Irish sculptor known for prominent public monuments and neoclassical works in Dublin.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65aef16588190b3a40a3d49ef5080 completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.