Triple

T10323234
Position Surface form Disambiguated ID Type / Status
Subject Suzie Gold E242691 entity
Predicate starring P1507 FINISHED
Object Rebecca Front E358616 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: Rebecca Front | Statement: [Suzie Gold, starring, Rebecca Front]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rebecca Front
Context triple: [Suzie Gold, starring, Rebecca Front]
  • A. Rebecca Front chosen
    Rebecca Front is a British actress and comedian best known for her roles in television series such as "The Thick of It," "Lewis," and numerous other UK comedies and dramas.
  • B. Stevie Crawford
    Stevie Crawford is a Scottish former professional footballer and coach best known as a prolific forward in the Scottish leagues and later as a manager.
  • C. Veronica Baker
    Veronica Baker is known as the daughter of Rick Baker, the acclaimed special makeup effects artist and seven-time Academy Award winner.
  • D. Tatia Starkey
    Tatia Starkey is an English bassist and vocalist, known for her work with bands such as Belakiss and for being the granddaughter of Beatles drummer Ringo Starr.
  • E. Karen Morley
    Karen Morley was an American film actress of the 1930s, best known for her roles in pre-Code Hollywood crime dramas and social-themed films.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d6cdb6cc8190b37ca4494287128b completed April 7, 2026, 10:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71da2053481908fe5ed097b480cdd completed April 9, 2026, 3:31 a.m.
Created at: April 6, 2026, 11:50 a.m.