Triple

T22592024
Position Surface form Disambiguated ID Type / Status
Subject Affirm Holdings, Inc. E564973 entity
Predicate foundedBy P104 FINISHED
Object Jeff Kaditz 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: Jeff Kaditz | Statement: [Affirm Holdings, Inc., foundedBy, Jeff Kaditz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeff Kaditz
Context triple: [Affirm Holdings, Inc., foundedBy, Jeff Kaditz]
  • A. Jeff Kaditz chosen
    Jeff Kaditz is an American entrepreneur and technologist best known as the co-founder and former CTO of the financial technology company Affirm.
  • B. Michael Karpf
    Michael Karpf is a British physician and academic leader best known for his roles in hospital administration and medical education.
  • C. John Kamps
    John Kamps is an American screenwriter best known for co-writing the family science fiction film "Zathura: A Space Adventure."
  • D. Ken Lauber
    Ken Lauber is an American composer and musician known for his film and television scores, blending elements of jazz, classical, and popular music.
  • E. John Daheim
    John Daheim was an American character actor who appeared in numerous film and television productions during the mid-20th century.
  • 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f16162c2cc8190a506776ac52356d7 completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:49 p.m.