Triple

T19469927
Position Surface form Disambiguated ID Type / Status
Subject Sweet Tooth E487093 entity
Predicate hasCharacter P2308 FINISHED
Object Serena Frome 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: Serena Frome | Statement: [Sweet Tooth, hasCharacter, Serena Frome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Serena Frome
Context triple: [Sweet Tooth, hasCharacter, Serena Frome]
  • A. Serena Frome chosen
    Serena Frome is the protagonist of Ian McEwan’s novel "Sweet Tooth," a young Cambridge graduate recruited into a covert MI5 operation in 1970s Britain.
  • B. Serena Tomalin
    Serena Tomalin is a British woman best known as one of the children of acclaimed biographer and literary journalist Claire Tomalin.
  • C. Serena Evans
    Serena Evans is a British actress best known for her role in the BBC sitcom "The Thin Blue Line."
  • D. Serena Benson
    Serena Benson is the late mother of NYPD Captain Olivia Benson in the television series "Law & Order: Special Victims Unit," whose traumatic history and alcoholism deeply influenced Olivia's life.
  • E. Serena Brown
    Serena Brown is the daughter of Bob Brown.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e6fd988190b79be580b65746fe completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:39 p.m.