Triple

T12255864
Position Surface form Disambiguated ID Type / Status
Subject Donald Davidson E292097 entity
Predicate spouse P13 FINISHED
Object Margeurite Davidson E292097 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: Margeurite Davidson | Statement: [Donald Davidson, spouse, Margeurite Davidson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margeurite Davidson
Context triple: [Donald Davidson, spouse, Margeurite Davidson]
  • A. Margeurite Davidson chosen
    Margeurite Davidson was the wife of influential American philosopher Donald Davidson.
  • B. Mabel Elizabeth Davies
    Mabel Elizabeth Davies was the mother of Canadian-American actor and comedian Leslie Nielsen.
  • C. Sarah Davis
    Sarah Davis was the mother of Rufus Isaacs, 1st Marquess of Reading, a prominent British lawyer, politician, and Viceroy of India.
  • D. Sarah Emily Davies
    Sarah Emily Davies was a pioneering 19th-century English feminist and educational reformer who played a key role in founding Girton College, Cambridge, one of the first residential colleges for women in England.
  • E. Marguerite Harrison
    Marguerite Harrison is an American documentary filmmaker best known for directing the 1999 film "Grass," which explores the history of marijuana prohibition in the United States.
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cc9dd5081908880061d52351850 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62a921b8c8190b3f899b03575b194 completed May 2, 2026, 4:47 p.m.
Created at: April 8, 2026, 9:52 p.m.