Triple

T18504867
Position Surface form Disambiguated ID Type / Status
Subject Shawn Johnson E452172 entity
Predicate twitterHandle P2866 FINISHED
Object @ShawnJohnson 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: @ShawnJohnson | Statement: [Shawn Johnson, twitterHandle, @ShawnJohnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: @ShawnJohnson
Context triple: [Shawn Johnson, twitterHandle, @ShawnJohnson]
  • A. @shawnjohnson chosen
    @shawnjohnson is the Instagram account of Shawn Johnson, the American Olympic gold medal–winning gymnast and media personality.
  • B. Sydney Johnson
    Sydney Johnson is an American basketball coach and former Princeton University point guard best known for leading the Princeton Tigers men’s basketball program in the late 2000s.
  • C. Shannon Johnson
    Shannon Johnson is a former American professional basketball player and WNBA All-Star point guard known for her playmaking and leadership in the league’s early years.
  • D. Shawn Andrews
    Shawn Andrews is an American actor best known for his role as Kevin Pickford in the cult classic film "Dazed and Confused."
  • E. Shawn Dou
    Shawn Dou is a Chinese-Canadian actor known for his breakout role in Zhang Yimou’s film "Under the Hawthorn Tree" and subsequent performances in both film and television dramas.
  • 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_69d8d386df84819092355ebb260d848e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53341063c81908361b0eb78794145 completed April 19, 2026, 7:55 p.m.
Created at: April 10, 2026, 11:36 a.m.