Triple

T19263851
Position Surface form Disambiguated ID Type / Status
Subject Carolyn Bessette-Kennedy E481718 entity
Predicate father P120 FINISHED
Object William J. Bessette NE NERFINISHED

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: William J. Bessette | Statement: [Carolyn Bessette-Kennedy, father, William J. Bessette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William J. Bessette
Context triple: [Carolyn Bessette-Kennedy, father, William J. Bessette]
  • A. William J. Bessette chosen
    William J. Bessette is best known as the father of Carolyn Bessette-Kennedy, the late wife of John F. Kennedy Jr.
  • B. Thomas J. Lahey
    Thomas J. Lahey was an individual of sufficient local significance—likely an educator or community leader—to have an elementary school named in his honor.
  • C. Charles E. Kearney
    Charles E. Kearney was a 19th-century American railroad executive and civic leader after whom the city of Kearney, Missouri, is named.
  • D. Arthur E. Molloy
    Arthur E. Molloy was an individual significant enough in marine or exploratory history to have the undersea feature Molloy Deep named in his honor.
  • E. William E. Walsh
    William E. Walsh was an American businessman and civic leader best known for playing a key role in the establishment of the University of Miami in the 1920s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8bce6881908395836960762672 completed April 20, 2026, 10:10 a.m.
Created at: April 10, 2026, 1:28 p.m.