Triple

T23101267
Position Surface form Disambiguated ID Type / Status
Subject The Castle E576036 entity
Predicate writer P1360 FINISHED
Object Jane Kennedy 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: Jane Kennedy | Statement: [The Castle, writer, Jane Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Kennedy
Context triple: [The Castle, writer, Jane Kennedy]
  • A. Jane Kennedy chosen
    Jane Kennedy is an Australian actress, comedian, writer, and producer best known as a member of The D-Generation and for her work on television shows such as Frontline and The Panel.
  • B. Mary Claire Kennedy
    Mary Claire Kennedy is the birth name of American actress and activist Mimi Kennedy, known for her work in television, film, and theater.
  • C. Jean Ann Kennedy
    Jean Ann Kennedy was an American socialite and philanthropist, a member of the prominent Kennedy family and sister of President John F. Kennedy.
  • D. Mary Courtney Kennedy
    Mary Courtney Kennedy is an American philanthropist and member of the Kennedy family, known as the daughter of Robert F. Kennedy and Ethel Skakel Kennedy.
  • E. Eunice Mary Kennedy
    Eunice Mary Kennedy was an American philanthropist and member of the Kennedy family best known for founding the Special Olympics and advocating for people with intellectual disabilities.
  • 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_69e245c060b48190a9bd61a47a16db17 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18de8c5b4819095cddf989cade60d completed April 29, 2026, 4:49 a.m.
Created at: April 17, 2026, 3:58 p.m.