Triple

T14507992
Position Surface form Disambiguated ID Type / Status
Subject Desiree Akhavan E340315 entity
Predicate starredIn P1668 FINISHED
Object The Bisexual E904106 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: The Bisexual | Statement: [Desiree Akhavan, starredIn, The Bisexual]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Bisexual
Context triple: [Desiree Akhavan, starredIn, The Bisexual]
  • A. The Bisexual chosen
    The Bisexual is a British comedy-drama television series that explores the romantic and sexual identity of a woman coming to terms with her bisexuality.
  • B. The Opposite of Sex
    The Opposite of Sex is a 1998 dark romantic comedy film in which Christina Ricci plays a cynical, manipulative teenager who wreaks havoc on the lives of those around her.
  • C. In & Out of The Closet
    In & Out of The Closet is a documentary film by Jacob Bernstein that explores LGBTQ+ identity, fashion, and self-expression.
  • D. Queer Lion
    Queer Lion is an independent collateral award presented at the Venice Film Festival to honor the best film with LGBTQ+ themes or queer culture representation.
  • E. The Blue Closet
    "The Blue Closet" is a narrative poem by William Morris that blends medieval imagery with dreamlike, enigmatic storytelling.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de94e40e44819084f323f8f9982b75 completed April 14, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94a7187c81909f173c2fb70509f5 completed May 8, 2026, 7:45 a.m.
Created at: April 10, 2026, 1:21 a.m.