Triple

T17606756
Position Surface form Disambiguated ID Type / Status
Subject Sweet Smell of Success E428852 entity
Predicate starring P1507 FINISHED
Object Sam Levene 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: Sam Levene | Statement: [Sweet Smell of Success, starring, Sam Levene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sam Levene
Context triple: [Sweet Smell of Success, starring, Sam Levene]
  • A. Sam Levene chosen
    Sam Levene was a prominent American stage and film actor best known for his comic and character roles in mid-20th-century Broadway productions and Hollywood movies.
  • B. John Levene
    John Levene is a British actor best known for playing UNIT soldier Sergeant Benton in the classic science fiction television series Doctor Who.
  • C. Philip Levene
    Philip Levene was a British television and film writer best known for his work on the 1960s spy series "The Avengers."
  • D. Sam Levine
    Sam Levine is an American animation director and storyboard artist known for co-directing the superhero comedy film "DC League of Super-Pets."
  • E. Max Braverman
    Max Braverman is a character from the television series "Parenthood," known as Adam and Kristina Braverman’s son who is diagnosed with Asperger’s syndrome.
  • 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_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46c4ccef08190aeaa88670364bd74 completed April 19, 2026, 5:46 a.m.
Created at: April 10, 2026, 5:51 a.m.