Triple

T1461106
Position Surface form Disambiguated ID Type / Status
Subject Brian Chesky E31512 entity
Predicate coFounderWith P2835 FINISHED
Object Joe Gebbia E30983 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: Joe Gebbia | Statement: [Brian Chesky, coFounderWith, Joe Gebbia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Gebbia
Context triple: [Brian Chesky, coFounderWith, Joe Gebbia]
  • A. Joe Gebbia chosen
    Joe Gebbia is an American designer and entrepreneur best known as a co-founder of the home-sharing platform Airbnb.
  • B. Dustin Moskovitz
    Dustin Moskovitz is an American entrepreneur and philanthropist best known as a co-founder of Facebook and the productivity software company Asana.
  • C. Jeff Weiner
    Jeff Weiner is an American business executive best known for serving as the longtime CEO of LinkedIn, where he oversaw the company’s rapid growth and acquisition by Microsoft.
  • D. Parker Bowles
    Parker Bowles is the surname of the British aristocratic family most prominently associated with Queen Camilla, the Queen Consort of the United Kingdom.
  • E. Andy Bernard
    Andy Bernard is a fictional, a cappella-loving salesman and later regional manager on the U.S. television series "The Office," known for his insecurity, anger issues, and musical outbursts.
  • 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_69a49917dfc081909acdbdf5d684f1ef completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c59ecb60819082217b034e18381f completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e7ab538819090bc3e3ed1bbff64 completed March 8, 2026, 5:51 a.m.
Created at: March 1, 2026, 8 p.m.