Triple

T22804668
Position Surface form Disambiguated ID Type / Status
Subject The OA E564498 entity
Predicate executiveProducer P7225 FINISHED
Object Brit Marling 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: Brit Marling | Statement: [The OA, executiveProducer, Brit Marling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brit Marling
Context triple: [The OA, executiveProducer, Brit Marling]
  • A. Brit Marling chosen
    Brit Marling is an American actress, writer, and producer best known for her work in thought-provoking independent films and for co-creating and starring in the Netflix series "The OA."
  • B. Kristin Linklater
    Kristin Linklater was a renowned Scottish vocal coach, teacher, and author best known for her influential work on voice training for actors and her long association with Shakespearean performance.
  • C. Elizabeth Burns
    Elizabeth Burns was a daughter of the Scottish poet Robert Burns, known primarily through her connection to his family and legacy.
  • D. Sian Heder
    Sian Heder is an American filmmaker and screenwriter best known for writing and directing the Academy Award–winning film "CODA."
  • E. Courtney Hunt
    Courtney Hunt is an American filmmaker best known for her acclaimed independent drama "Frozen River," which earned multiple award nominations including an Academy Award for Best Original Screenplay.
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17d5b37cc8190a41d8f304ba8d609 completed April 29, 2026, 3:39 a.m.
Created at: April 17, 2026, 3:31 p.m.