Triple

T13498570
Position Surface form Disambiguated ID Type / Status
Subject Ethel Lina White E320823 entity
Predicate notableWork P4 FINISHED
Object Some Must Watch E320822 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: Some Must Watch | Statement: [Ethel Lina White, notableWork, Some Must Watch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Some Must Watch
Context triple: [Ethel Lina White, notableWork, Some Must Watch]
  • A. Some Must Watch chosen
    Some Must Watch is a 1941 suspense novel by Ethel Lina White, best known as the source material for the classic thriller film The Spiral Staircase.
  • B. Must See TV
    Must See TV was NBC’s famous 1990s promotional brand for its highly popular prime-time comedy lineup, especially on Thursday nights.
  • C. One to Watch
    One to Watch is an award category at the Golden Joystick Awards that highlights upcoming or highly anticipated video games yet to be released.
  • D. Let Me Watch
    Let Me Watch is a track featured on the album "Evolver."
  • E. Watching Brief
    Watching Brief is a book by Australian barrister and human rights advocate Julian Burnside that reflects on law, justice, and civil liberties through his legal experiences.
  • 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_69d807629d6c8190998f1b9bb12d2ed0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaf4fab688190bdc746985b0c7338 completed April 12, 2026, 2:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76ba566c48190808857dd0bc3a871 completed May 3, 2026, 3:37 p.m.
Created at: April 9, 2026, 9:43 p.m.