Triple

T15490340
Position Surface form Disambiguated ID Type / Status
Subject Tom Boonen E378665 entity
Predicate name P16 FINISHED
Object Tom Boonen E378665 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: Tom Boonen | Statement: [Tom Boonen, name, Tom Boonen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Boonen
Context triple: [Tom Boonen, name, Tom Boonen]
  • A. Tom Boonen chosen
    Tom Boonen is a retired Belgian professional cyclist renowned as one of the greatest classics specialists of his era, particularly dominant in the cobbled Monuments.
  • B. Josh Molina
    Josh Molina is an American actor best known for his roles in television series such as The West Wing and Scandal.
  • C. Pat Burrell
    Pat Burrell is a former Major League Baseball outfielder and World Series champion best known for his power hitting with the Philadelphia Phillies and San Francisco Giants.
  • D. Stephen Drew
    Stephen Drew is an American former Major League Baseball shortstop known for his years with the Arizona Diamondbacks and Boston Red Sox, including helping the Red Sox win the 2013 World Series.
  • E. Prince Fielder
    Prince Fielder is a former Major League Baseball first baseman known for his prodigious power hitting and multiple All-Star seasons, primarily with the Milwaukee Brewers and Detroit Tigers.
  • 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_69d85cd53a7c819080f5b9042c4c199e completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03fac2af88190ac1d119e6b21dbe0 completed April 16, 2026, 1:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff365f27c48190822254b6da504d3d completed May 9, 2026, 1:27 p.m.
Created at: April 10, 2026, 3:48 a.m.