Triple

T18222580
Position Surface form Disambiguated ID Type / Status
Subject Kay Thorndyke E436341 entity
Predicate conflictsWith P4897 FINISHED
Object Mary Matthews 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 Matthews | Statement: [Kay Thorndyke, conflictsWith, Mary Matthews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Matthews
Context triple: [Kay Thorndyke, conflictsWith, Mary Matthews]
  • A. Mary Matthews chosen
    Mary Matthews is the idealistic socialite protagonist of the 1945 political drama film "State of the Union," who becomes entangled in her husband's bid for the U.S. presidency.
  • B. Mary Bullock
    Mary Bullock was the wife of Amos Kendall, a prominent 19th-century American journalist, politician, and U.S. Postmaster General.
  • C. Rose Matthews
    Rose Matthews is the daughter of English socialite and author Pippa Middleton and her husband James Matthews.
  • D. Sarah Matthews
    Sarah Matthews is the protagonist of the film "Made in America," around whom the story’s central family and identity themes revolve.
  • E. Sarah Matthews
    Sarah Matthews is an American communications professional and former White House deputy press secretary who served in the Trump administration and later testified before the U.S. House committee investigating the January 6 Capitol attack.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47c85108190bd9707b40bdfdb38 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.