Triple

T11012621
Position Surface form Disambiguated ID Type / Status
Subject Ruth Nidesand E260278 entity
Predicate spouse P13 FINISHED
Object Barack Obama Sr. E8294 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: Barack Obama Sr. | Statement: [Ruth Nidesand, spouse, Barack Obama Sr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barack Obama Sr.
Context triple: [Ruth Nidesand, spouse, Barack Obama Sr.]
  • A. Barack Obama Sr. chosen
    Barack Obama Sr. was a Kenyan economist and government official best known as the father of U.S. President Barack Obama.
  • B. Bernard Obama
    Bernard Obama is a Kenyan man known primarily as a member of Barack Obama’s extended family and the brother of Auma Obama.
  • C. Stanley Armour Dunham
    Stanley Armour Dunham was an American furniture salesman and World War II veteran best known as the maternal grandfather of U.S. President Barack Obama.
  • D. Roy Obama
    Roy Obama is a Kenyan-born half-brother of former U.S. President Barack Obama, known primarily as a member of the Obama family.
  • E. George Walker Weld
    George Walker Weld was an American philanthropist from a prominent Boston family, best known for funding Harvard University's Weld Boathouse and supporting rowing and other athletic pursuits.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7978a57a881909b4ceae0ebe21b78 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e374ac78348190a8c0a5a7a736b24b completed April 18, 2026, 12:10 p.m.
Created at: April 8, 2026, 9:25 p.m.