Triple

T8019797
Position Surface form Disambiguated ID Type / Status
Subject George W. Bush E186709 entity
Predicate spouse P13 FINISHED
Object Laura Bush E53705 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: Laura Bush | Statement: [George W. Bush, spouse, Laura Bush]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Bush
Context triple: [George W. Bush, spouse, Laura Bush]
  • A. Laura Bush chosen
    Laura Bush is an American educator and former librarian who served as First Lady of the United States from 2001 to 2009 during the presidency of her husband, George W. Bush.
  • B. Barbara Bush
    Barbara Bush was the former First Lady of the United States and a prominent advocate for family literacy, known for her down-to-earth style and public service.
  • C. Amy Carter
    Amy Carter is the daughter of former U.S. President Jimmy Carter, known for growing up in the White House and later engaging in political activism and illustration.
  • D. Mary Cheney
    Mary Cheney is an American political consultant and the openly lesbian daughter of former U.S. Vice President Dick Cheney, known for her involvement in Republican politics and LGBT advocacy.
  • E. Michelle Obama
    Michelle Obama is an American lawyer, author, and former First Lady of the United States known for her advocacy on education, health, and military families.
  • 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_69ca82ac7fc081909b1398cf025423af completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3e8bc90081909f6f5878e6f1f241 completed March 31, 2026, 3:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbe3243348190bd4e9073e5460386 completed April 1, 2026, 6:41 a.m.
Created at: March 30, 2026, 5:20 p.m.