Triple

T6597425
Position Surface form Disambiguated ID Type / Status
Subject Neil Jordan E148510 entity
Predicate wroteScreenplayFor P15305 FINISHED
Object Greta (2018 film) E601607 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: Greta (2018 film) | Statement: [Neil Jordan, wroteScreenplayFor, Greta (2018 film)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greta (2018 film)
Context triple: [Neil Jordan, wroteScreenplayFor, Greta (2018 film)]
  • A. Greta (2018 film) chosen
    Greta is a 2018 psychological thriller film about a young woman who befriends a seemingly lonely older widow, only to discover her increasingly obsessive and dangerous behavior.
  • B. "I Am Greta"
    "I Am Greta" is a documentary film that follows climate activist Greta Thunberg’s rise from solitary school striker to global environmental icon.
  • C. Greta
    Greta is a small town located within the Hunter Region of New South Wales, Australia.
  • D. Greta
    Greta is a feminine given name, commonly used as a diminutive or variant of names like Margaret in various European languages.
  • E. Elle
    Elle is the solitary female protagonist of Francis Poulenc’s one-act opera *La voix humaine*, whose intense telephone monologue lays bare her emotional collapse during a breakup.
  • 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_69c687e7b8688190811ffee72e096468 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6aeee738081908913f4f8c6699bd9 completed March 27, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6eedfe3a88190a1d7fda9ff0dc9bd completed March 27, 2026, 8:56 p.m.
Created at: March 27, 2026, 1:56 p.m.