Triple

T2268827
Position Surface form Disambiguated ID Type / Status
Subject Auma Obama E50609 entity
Predicate mother P120 FINISHED
Object Kezia Aoko E50254 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: Kezia Aoko | Statement: [Auma Obama, mother, Kezia Aoko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kezia Aoko
Context triple: [Auma Obama, mother, Kezia Aoko]
  • A. Kezia Aoko chosen
    Kezia Aoko is the first wife of Barack Obama Sr. and the stepmother of former U.S. President Barack Obama.
  • B. Aurora Zogoiby
    Aurora Zogoiby is a central figure in Salman Rushdie’s novel "The Moor’s Last Sigh," portrayed as a fiercely independent, controversial Indian artist whose life and work profoundly shape the story’s family saga.
  • C. Chaia King
    Chaia King was an American author and the daughter of legendary television and radio host Larry King.
  • D. Mariana Keil
    Mariana Keil is known primarily as a daughter of the Portuguese composer and painter Alfredo Keil, who wrote the music for Portugal’s national anthem.
  • E. Yvonne Zima
    Yvonne Zima is an American actress known for her work as a child performer in films and television, including notable roles in 1990s thrillers and popular TV dramas.
  • 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_69a88b05910c8190a9a2b1ff230c85f9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc1bd376c8190a43decde599f62e6 completed March 7, 2026, 6:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71d70e488190a2f8276dd7a7bf9e completed March 9, 2026, 7:08 a.m.
Created at: March 4, 2026, 7:48 p.m.