Triple

T19962803
Position Surface form Disambiguated ID Type / Status
Subject David Seymour E479856 entity
Predicate coFounderWith P2835 FINISHED
Object William Vandivert 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: William Vandivert | Statement: [David Seymour, coFounderWith, William Vandivert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Vandivert
Context triple: [David Seymour, coFounderWith, William Vandivert]
  • A. William Vandivert chosen
    William Vandivert was an American photojournalist best known as one of the founding members of the Magnum Photos cooperative.
  • B. Frederick Henry Litchfield
    Frederick Henry Litchfield was a 19th-century Australian explorer and pastoralist known for his expeditions in the Northern Territory, for which Litchfield National Park is named in his honor.
  • C. Samuel Vassall
    Samuel Vassall was a 17th-century English merchant and politician known for resisting King Charles I’s illegal customs duties and later serving as a Member of Parliament.
  • D. John Redford
    John Redford was a prominent 16th-century English composer, organist, and dramatist associated with the Tudor court and early Anglican church music.
  • E. Henry Bemis
    Henry Bemis is the nearsighted, book-loving bank clerk from the classic Twilight Zone episode "Time Enough at Last," known for surviving a nuclear attack only to face a cruel twist of fate involving his beloved reading.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65af51b4c81909ba156a489cbc551 completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.