Triple

T21217891
Position Surface form Disambiguated ID Type / Status
Subject John Briley E522883 entity
Predicate wrote P2831 FINISHED
Object Marie 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: Marie | Statement: [John Briley, wrote, Marie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie
Context triple: [John Briley, wrote, Marie]
  • A. Marie chosen
    "Marie" is a 1985 biographical drama film directed by Roger Donaldson, depicting the true story of whistleblower Marie Ragghianti’s fight against political corruption in Tennessee.
  • B. Marie
    Marie is an individual known primarily as the spouse of Jess.
  • C. Marie
    Marie is a fictional character from the American sitcom "Vinnie & Bobby," which followed two construction workers navigating life and relationships in Chicago.
  • D. Marie
    "Marie" is a popular jazz and big band standard composed by Thomas "Tommy" Dorsey that became one of his signature recordings.
  • E. Marie
    Marie is one of the Squid Sisters, a popular idol duo from Nintendo’s Splatoon series known for hosting in-game news and events.
  • 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_69e0b511ed84819099b449b4a111085c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7347613308190a1c9f4ea51591d4b completed April 21, 2026, 8:25 a.m.
Created at: April 16, 2026, 3:42 p.m.