Triple

T2804790
Position Surface form Disambiguated ID Type / Status
Subject Naomi Biden E54025 entity
Predicate childOf P120 FINISHED
Object Kathleen Buhle E269004 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: Kathleen Buhle | Statement: [Naomi Biden, childOf, Kathleen Buhle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kathleen Buhle
Context triple: [Naomi Biden, childOf, Kathleen Buhle]
  • A. Kathleen Buhle chosen
    Kathleen Buhle is an American nonprofit executive and author best known as the ex-wife of Hunter Biden and for her memoir detailing their marriage and divorce.
  • B. Kathleen Middlekauff
    Kathleen Middlekauff is an American academic and former spouse of investigative journalist and author Bob Woodward.
  • C. Barbara Franklin
    Barbara Franklin is an American business executive and former U.S. Secretary of Commerce known for advancing women’s roles in government and corporate leadership.
  • D. Margaret Pomeranz
    Margaret Pomeranz is an Australian film critic and television presenter best known for co-hosting long-running movie review programs such as "The Movie Show" and "At the Movies."
  • E. Cathy A. Sandeen
    Cathy A. Sandeen is an American academic leader and administrator known for serving as president of multiple public universities in the United States.
  • 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_69ab49dcee188190b5c6eca9ae9e3469 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde1525888190b3c04e10043c67d6 completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc674217c81908177b088cc824e7b completed March 10, 2026, 7:21 a.m.
Created at: March 6, 2026, 9:59 p.m.