Triple

T23298366
Position Surface form Disambiguated ID Type / Status
Subject The Phone Call E590233 entity
Predicate starring P1507 FINISHED
Object Prunella Scales 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: Prunella Scales | Statement: [The Phone Call, starring, Prunella Scales]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prunella Scales
Context triple: [The Phone Call, starring, Prunella Scales]
  • A. Prunella Scales chosen
    Prunella Scales is an English actress best known for her comic role as Sybil Fawlty in the classic British sitcom "Fawlty Towers."
  • B. Hermione Norris
    Hermione Norris is an English actress best known for her roles in television dramas such as "Cold Feet," "Spooks," and "Wire in the Blood."
  • C. Liz Henson
    Liz Henson is a character in the film "Dogville," appearing as one of the townspeople who interact with the protagonist Grace Margaret Mulligan.
  • D. Ruthie Henshall
    Ruthie Henshall is an acclaimed British musical theatre actress and singer known for her leading roles in major West End and Broadway productions.
  • E. Hermione Baddeley
    Hermione Baddeley was an English character actress known for her sharp-tongued, memorable supporting roles in British cinema and later in Hollywood films and television.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d083188190abaae77dd4cf2bae completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.