Triple

T23319440
Position Surface form Disambiguated ID Type / Status
Subject Taylor Wright E590806 entity
Predicate hasFamilyName P18 FINISHED
Object Wright 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: Wright | Statement: [Taylor Wright, hasFamilyName, Wright]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wright
Context triple: [Taylor Wright, hasFamilyName, Wright]
  • A. Wright chosen
    Wright is a common English surname borne by numerous notable individuals across politics, sports, arts, and science.
  • B. Wright
    Wright is the surname of Tré Cool, the German-born American drummer best known for his work with the punk rock band Green Day.
  • C. Wright
    Wright is an Australian federal electoral division in Queensland represented in the House of Representatives.
  • D. Wright-Martin
    Wright-Martin was an early 20th-century American aircraft engine and aviation company known for producing licensed versions of European aero engines during World War I.
  • E. Wrightman
    Wrightman is the surname of actress Frieda Inescort, used as her family name in personal and professional records.
  • 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_69e25d1d32188190948eb76909d1dcc3 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1978440888190b316664812105d60 completed April 29, 2026, 5:30 a.m.
Created at: April 17, 2026, 5:07 p.m.