Triple

T20712683
Position Surface form Disambiguated ID Type / Status
Subject Evan Sharp E509086 entity
Predicate coFounderWith P2835 FINISHED
Object Paul Sciarra 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: Paul Sciarra | Statement: [Evan Sharp, coFounderWith, Paul Sciarra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Sciarra
Context triple: [Evan Sharp, coFounderWith, Paul Sciarra]
  • A. Paul Sciarra chosen
    Paul Sciarra is an American entrepreneur best known as a co-founder of the visual discovery and bookmarking platform Pinterest.
  • B. Joe D'Arco
    Joe D'Arco is a musician best known as a former member of the American rock band Godsmack.
  • C. Tony Corrente
    Tony Corrente is an American football official best known for his long NFL refereeing career, including serving as the head referee for multiple high-profile games.
  • D. Tony DeMarco
    Tony DeMarco was an American professional boxer and former world welterweight champion known for his aggressive, crowd-pleasing fighting style during the 1950s.
  • E. Eddie Morra
    Eddie Morra is a struggling writer who gains extraordinary cognitive abilities after taking a mysterious nootropic drug in the film "Limitless."
  • 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_69e0b4c40ad88190b81f77695366d328 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1ce84e48190922db93ed4b5d21b completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:15 p.m.