Triple

T2057485
Position Surface form Disambiguated ID Type / Status
Subject Stanley Armour Dunham E45706 entity
Predicate relative P37 FINISHED
Object Madelyn Dunham E47158 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: Madelyn Dunham | Statement: [Stanley Armour Dunham, relative, Madelyn Dunham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madelyn Dunham
Context triple: [Stanley Armour Dunham, relative, Madelyn Dunham]
  • A. Madelyn Dunham chosen
    Madelyn Dunham was the maternal grandmother of Barack Obama and a key figure in his upbringing in Hawaii.
  • B. Anne Miller
    Anne Miller is best known as the wife of acclaimed Irish-English actor Michael Gambon.
  • C. Aline Brosh McKenna
    Aline Brosh McKenna is an American screenwriter, producer, and director best known for her sharp, character-driven work on films and television series such as The Devil Wears Prada and Crazy Ex-Girlfriend.
  • D. Jean Kerr McCarthy
    Jean Kerr McCarthy was the wife of U.S. Senator Joseph McCarthy and a conservative political figure who supported and helped manage aspects of his controversial anti-communist career.
  • E. Julia Compton Moore
    Julia Compton Moore was a U.S. Army spouse and advocate who played a pivotal role in improving casualty notification and support for military families during and after the Vietnam War.
  • 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_69a8891a19508190a12ef1e192308dcb completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9ae0130819089f7d62005466a45 completed March 7, 2026, 5:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae271cb26c81908664f4c26f4fb5ea completed March 9, 2026, 1:49 a.m.
Created at: March 4, 2026, 7:40 p.m.