Triple

T20173619
Position Surface form Disambiguated ID Type / Status
Subject Everson Walls E492032 entity
Predicate name P16 FINISHED
Object Everson Walls 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: Everson Walls | Statement: [Everson Walls, name, Everson Walls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Everson Walls
Context triple: [Everson Walls, name, Everson Walls]
  • A. Everson Walls chosen
    Everson Walls is a former NFL cornerback best known for leading the league in interceptions multiple times and winning a Super Bowl with the Dallas Cowboys and New York Giants.
  • B. Joe Dilworth
    Joe Dilworth is an English drummer and photographer best known for his early work with the avant-pop band Stereolab and his influential music photography.
  • C. Ken Waller
    Ken Waller is an American bodybuilder best known for his appearances in the 1970s bodybuilding scene and his prominent role in the documentary film "Pumping Iron."
  • D. Dade Faison
    Dade Faison is one of the children of actor Donald Faison and his former partner Lisa Askey.
  • E. Andrew Wells
    Andrew Wells is a music producer known for his work on the album "Hurts 2B Human."
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6684a33688190b22cfc16907e76bc completed April 20, 2026, 5:54 p.m.
Created at: April 11, 2026, 11:36 p.m.