Triple

T17151772
Position Surface form Disambiguated ID Type / Status
Subject Kerry family E416238 entity
Predicate notableMember P10 FINISHED
Object Alexandra Kerry E921695 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: Alexandra Kerry | Statement: [Kerry family, notableMember, Alexandra Kerry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alexandra Kerry
Context triple: [Kerry family, notableMember, Alexandra Kerry]
  • A. Alexandra Kerry chosen
    Alexandra Kerry is an American filmmaker and producer, known for her documentary work and as the daughter of politician John Kerry and writer Julia Thorne.
  • B. Katherine McAuliffe
    Katherine McAuliffe is a developmental psychologist known for her research on the emergence of fairness, cooperation, and moral reasoning in children across cultures.
  • C. Victoria Knox
    Victoria Knox is the main antagonist in the action-comedy film "Barely Lethal," portrayed as a dangerous and cunning arms dealer.
  • D. Alexandra Stewart
    Alexandra Stewart is a Canadian-born actress known for her work in European and American cinema, including prominent roles in French New Wave and art-house films.
  • E. Kathryn Alexander
    Kathryn Alexander is known as the daughter of American politician and former U.S. Senator Lamar Alexander.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f40775848190ada44742c0113ab3 completed April 18, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0148337a348190b8739eb3f553f1d9 completed May 11, 2026, 3:08 a.m.
Created at: April 10, 2026, 5:36 a.m.