Triple

T2149985
Position Surface form Disambiguated ID Type / Status
Subject Barack Obama E47156 entity
Predicate mother P120 FINISHED
Object Ann Dunham E7435 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: Ann Dunham | Statement: [Barack Obama, mother, Ann Dunham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ann Dunham
Context triple: [Barack Obama, mother, Ann Dunham]
  • A. Ann Dunham chosen
    Ann Dunham was an American anthropologist and development specialist best known as the mother of U.S. President Barack Obama.
  • B. Jill Ker Conway
    Jill Ker Conway was an Australian-American historian, memoirist, and educator best known as the first female president of Smith College and for her influential autobiographical writings.
  • C. Pamela Gail Putnam
    Pamela Gail Putnam is known as the first wife of Michael Reagan, the adopted son of former U.S. President Ronald Reagan and actress Jane Wyman.
  • D. Jean Rogers
    Jean Rogers is known as the wife of American country music singer and songwriter Kenny Rogers.
  • E. Damaris Hopkins
    Damaris Hopkins was a young girl who traveled on the Mayflower as a member of Stephen Hopkins’ family in 1620.
  • 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_69a88a1933e0819094f18426ed74180f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe45dbf481909c0da056a1a99ece completed March 7, 2026, 5:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71af0fa081909dd4b2a7452623da completed March 9, 2026, 7:07 a.m.
Created at: March 4, 2026, 7:44 p.m.