Triple

T20950369
Position Surface form Disambiguated ID Type / Status
Subject Paul Kantner E515959 entity
Predicate child P120 FINISHED
Object China Kantner 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: China Kantner | Statement: [Paul Kantner, child, China Kantner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: China Kantner
Context triple: [Paul Kantner, child, China Kantner]
  • A. China Kantner chosen
    China Kantner is an American former actress and MTV VJ, best known as the daughter of Jefferson Airplane/Starship musicians Grace Slick and Paul Kantner.
  • B. Elliott Kastner
    Elliott Kastner was an American film producer known for backing notable movies such as "Sleuth" (1972) and "Where Eagles Dare."
  • C. Chieko Schrader
    Chieko Schrader is the wife of American screenwriter and director Leonard Schrader, known primarily in relation to his personal life.
  • D. Kenzi Isoda
    Kenzi Isoda is a Japanese film producer best known for his work on the acclaimed kaiju movie "Godzilla Minus One."
  • E. Michael Kunze
    Michael Kunze is a German lyricist, librettist, and playwright best known for his work on major German-language musical theatre productions and pop song lyrics.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadd3bd88190a0d1fdea9d300fc0 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:23 p.m.