Triple

T19678534
Position Surface form Disambiguated ID Type / Status
Subject John Wilkes E472518 entity
Predicate child P120 FINISHED
Object Mary Wilkes 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: Mary Wilkes | Statement: [John Wilkes, child, Mary Wilkes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Wilkes
Context triple: [John Wilkes, child, Mary Wilkes]
  • A. Mary Wilkes chosen
    Mary Wilkes is the daughter of the 18th-century English radical politician and journalist John Wilkes.
  • B. Mary Bowne
    Mary Bowne was a colonial-era New Yorker known primarily as the daughter of Quaker pioneer and religious freedom advocate John Bowne.
  • C. Mary Pratt
    Mary Pratt was a prominent Canadian realist painter renowned for her luminous, intimate depictions of everyday domestic scenes.
  • D. Margaret Corbin
    Margaret Corbin was an American Revolutionary War heroine who took over her fallen husband's cannon during battle, becoming one of the first women to fight in the war and receive a military pension.
  • E. Martha Rainsborough
    Martha Rainsborough is a notable individual associated with the Rainsborough family name, recognized as a significant bearer of that surname.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e641bda8348190b0c7816c50aca923 completed April 20, 2026, 3:09 p.m.
Created at: April 10, 2026, 1:45 p.m.