Triple

T22944521
Position Surface form Disambiguated ID Type / Status
Subject Patrick Collison E569828 entity
Predicate familyName P18 FINISHED
Object Collison 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: Collison | Statement: [Patrick Collison, familyName, Collison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Collison
Context triple: [Patrick Collison, familyName, Collison]
  • A. Collison chosen
    Collison is a surname most notably associated with American former NBA player Nick Collison and Irish tech entrepreneurs Patrick and John Collison.
  • B. Cloyce
    Cloyce is a surname most notably associated with Sarah Cloyce, one of the women accused during the Salem witch trials in 17th-century Massachusetts.
  • C. Conoley
    Conoley is the surname of Jane Close Conoley, an American psychologist and academic administrator known for serving as president of California State University, Long Beach.
  • D. Lamon
    Lamon is an archaeological site notable for inscriptions in the ancient Venetic language.
  • E. Battier
    Battier is the surname of Shane Battier, a retired American professional basketball player known for his defensive prowess and championship success in the NBA.
  • 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_69e2459199d08190a8184ee2aa935842 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1819c696c8190977bd2bca01509bc completed April 29, 2026, 3:57 a.m.
Created at: April 17, 2026, 3:45 p.m.