Triple

T23486940
Position Surface form Disambiguated ID Type / Status
Subject Flo (TV series) E570558 entity
Predicate hasCastMember P2308 FINISHED
Object Sudie Bond 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: Sudie Bond | Statement: [Flo (TV series), hasCastMember, Sudie Bond]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sudie Bond
Context triple: [Flo (TV series), hasCastMember, Sudie Bond]
  • A. Sudie Bond chosen
    Sudie Bond was an American character actress known for her work in film, television, and theater, often appearing in supporting comedic and dramatic roles.
  • B. Bullard
    Bullard is an English surname borne by various notable figures, including diplomats, politicians, and artists.
  • C. Sedol
    Sedol is the given name of Lee Sedol, the renowned South Korean professional Go player known for his historic matches against AI.
  • D. Bonde
    Bonde is a Swedish noble family name historically associated with influential political and landowning elites.
  • E. Brady bonds
    Brady bonds are U.S. dollar–denominated sovereign debt securities issued by emerging market countries in the late 1980s and 1990s to restructure and reduce their commercial bank debt.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a754825481909b005ca5654c3159 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:04 p.m.