Triple

T16645444
Position Surface form Disambiguated ID Type / Status
Subject Richard Reed E404455 entity
Predicate businessPartner P282 FINISHED
Object Jon Wright E418068 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: Jon Wright | Statement: [Richard Reed, businessPartner, Jon Wright]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jon Wright
Context triple: [Richard Reed, businessPartner, Jon Wright]
  • A. Jon Wright chosen
    Jon Wright is a British entrepreneur best known as one of the co-founders of the smoothie and juice company Innocent Drinks.
  • B. Tony Wright
    Tony Wright was a British actor best known for his film and television work in the 1950s and 1960s.
  • C. Andrew Wilson
    Andrew Wilson is an American actor and director, and the eldest of the Wilson brothers known for their work in films such as "Bottle Rocket" and "The Royal Tenenbaums."
  • D. Sam Wright
    Sam Wright is an individual known primarily as a relative of George Wright.
  • E. Tom Wright
    Tom Wright is a British architect best known for designing Dubai’s iconic sail-shaped Burj Al Arab hotel.
  • 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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37ad4735c81908a3a227bf02ca489 completed April 18, 2026, 12:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00918e61ac8190a01baf353a6a745c completed May 10, 2026, 2:09 p.m.
Created at: April 10, 2026, 5:18 a.m.