Triple

T20712639
Position Surface form Disambiguated ID Type / Status
Subject Ben Silbermann E509085 entity
Predicate coFounderWith P2835 FINISHED
Object Evan Sharp 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: Evan Sharp | Statement: [Ben Silbermann, coFounderWith, Evan Sharp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evan Sharp
Context triple: [Ben Silbermann, coFounderWith, Evan Sharp]
  • A. Evan Sharp chosen
    Evan Sharp is an American designer and entrepreneur best known as a co-founder and former Chief Creative Officer of the visual discovery platform Pinterest.
  • B. Evan Ziporyn
    Evan Ziporyn is an American composer, clarinetist, and founding member of the Bang on a Can All-Stars known for his innovative fusion of Western contemporary music with Balinese gamelan and other non-Western traditions.
  • C. Evan Ross
    Evan Ross is an American actor and musician, known for his film and television roles and as the son of legendary singer Diana Ross.
  • D. Evan Stern
    Evan Stern is a Canadian actor best known for playing the quirky character Roald on the comedy series "Letterkenny."
  • E. Eli Nunn
    Eli Nunn is the child of English actress and writer Imogen Stubbs.
  • 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.