Triple

T1251372
Position Surface form Disambiguated ID Type / Status
Subject Deion Branch E26882 entity
Predicate givenName P17 FINISHED
Object Deion E26882 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: Deion | Statement: [Deion Branch, givenName, Deion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deion
Context triple: [Deion Branch, givenName, Deion]
  • A. Deion Branch chosen
    Deion Branch is a former NFL wide receiver best known for his standout performances with the New England Patriots, including earning Super Bowl MVP honors.
  • B. Haven Daboll
    Haven Daboll is a member of the Daboll family, known publicly as a relative of NFL head coach Brian Daboll.
  • C. Deacon Jones
    Deacon Jones was a dominant NFL defensive end, famed for popularizing the term "sack" and becoming one of the most feared pass rushers in football history.
  • D. Darnell Donerson
    Darnell Donerson was the mother of singer and actress Jennifer Hudson, tragically known for her murder in 2008.
  • E. Isaiah Rogers
    Isaiah Rogers was a prominent 19th-century American architect known for pioneering hotel design and contributing major public buildings in the United States.
  • 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_69a49487a9c48190ba9b05348fd1b53f completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4bf85e1e08190ba6aac3fcd8bb3e7 completed March 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac93c66bf881908f4b63548341178e completed March 7, 2026, 9:08 p.m.
Created at: March 1, 2026, 7:47 p.m.