Triple

T8416825
Position Surface form Disambiguated ID Type / Status
Subject 1984 (television commercial) E198747 entity
Predicate editor P1954 FINISHED
Object Pip Baker E353333 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: Pip Baker | Statement: [1984 (television commercial), editor, Pip Baker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pip Baker
Context triple: [1984 (television commercial), editor, Pip Baker]
  • A. Pip Baker chosen
    Pip Baker was a British television writer best known for co-writing several 1980s Doctor Who serials with his wife Jane Baker.
  • B. Pip Karmel
    Pip Karmel is an Australian film editor and director best known for her acclaimed editing work on the film "Shine."
  • C. Pip Torrens
    Pip Torrens is a British actor known for his character roles in film and television, including appearances in series such as "Patrick Melrose," "The Crown," and "Preacher."
  • D. Noël Piper
    Noël Piper is an American Christian author and speaker known for her writings on faith, family, and hospitality, and for her long-time ministry partnership with her husband, theologian John Piper.
  • E. Pip Williams
    Pip Williams is a child of Rowan Williams, the former Archbishop of Canterbury and prominent theologian.
  • 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_69ca831201b481909e137936ef99ff11 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb84c5121081908efa3eca25406d3a completed March 31, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce0333a3488190ba30d03b1d7bacb1 completed April 2, 2026, 5:48 a.m.
Created at: March 30, 2026, 6:06 p.m.