Triple

T20472802
Position Surface form Disambiguated ID Type / Status
Subject Cory Ellison E502233 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Alex Levy 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: Alex Levy | Statement: [Cory Ellison, associatedWithCharacter, Alex Levy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alex Levy
Context triple: [Cory Ellison, associatedWithCharacter, Alex Levy]
  • A. Alex Levy chosen
    Alex Levy is a prominent fictional television news anchor and co-host at a major morning show, portrayed by Jennifer Aniston in the drama series "The Morning Show."
  • B. Jonathan Levy
    Jonathan Levy is a central character in the 2021 television miniseries "Scenes from a Marriage," serving as one half of the story’s intensely examined romantic relationship.
  • C. Michael Levy
    Michael Levy is a film producer known for his work on the action-crime drama movie "Waist Deep."
  • D. Matthew Levy
    Matthew Levy is an actor known for his role in the television sitcom "Sons of Tucson."
  • E. Sam Levy
    Sam Levy is an American cinematographer best known for his frequent collaborations with director Noah Baumbach and his work on acclaimed independent films.
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69962d810819091bb13fe73250e24 completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.