Triple

T14528155
Position Surface form Disambiguated ID Type / Status
Subject Bolt E340832 entity
Predicate storyBy P1955 FINISHED
Object Sam Levine E599174 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: Sam Levine | Statement: [Bolt, storyBy, Sam Levine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sam Levine
Context triple: [Bolt, storyBy, Sam Levine]
  • A. Sam Levine chosen
    Sam Levine is an American animation director and storyboard artist known for co-directing the superhero comedy film "DC League of Super-Pets."
  • B. 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.
  • C. Robert Levine
    Robert Levine is an American cardiologist best known as the husband of actress Mary Tyler Moore.
  • D. Nat Levine
    Nat Levine was an American film producer best known for founding Mascot Pictures and producing popular movie serials during the 1920s and 1930s.
  • E. Leon Levy
    Leon Levy was an American investor, philanthropist, and patron of the humanities known for his significant support of archaeology, the arts, and biographical scholarship.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea051bc608190ad4d516c5e7bca43 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0180bd1e5c8190a6a96581ce8a37de completed May 11, 2026, 7:09 a.m.
Created at: April 10, 2026, 1:22 a.m.