Triple
T38687696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evander Holyfield vs. Bert Cooper |
E949163
|
entity |
| Predicate | holyfieldTitlesDefended |
P33242
|
FINISHED |
| Object | WBA heavyweight title |
—
|
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: WBA heavyweight title | Statement: [Evander Holyfield vs. Bert Cooper, holyfieldTitlesDefended, WBA heavyweight title]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holyfieldTitlesDefended Context triple: [Evander Holyfield vs. Bert Cooper, holyfieldTitlesDefended, WBA heavyweight title]
-
A.
holyfieldKnockedDown
Indicates that Holyfield caused another participant to be knocked down, typically by delivering a blow that sent them to the canvas in a fight.
-
B.
numberOfTitleDefenses
chosen
Indicates the number of times an entity has successfully defended a previously won title or championship.
-
C.
defendedTitlesAcross
Indicates that a champion has successfully defended their title across multiple events, locations, or time periods.
-
D.
worldChampionshipTitles
Indicates the number of world championship titles an entity has won.
-
E.
undefeatedInProfessionalBoxing
Indicates that a boxer has never lost any match in their professional boxing career.
- F. None of above.
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_69f76efe16148190befd5dd59c3dfeaa |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: May 3, 2026, 4:33 p.m.