Triple
T12512265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jermain Taylor |
E299107
|
entity |
| Predicate | resultAgainstBernardHopkinsI |
P34090
|
FINISHED |
| Object | win by split decision |
—
|
LITERAL 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: win by split decision | Statement: [Jermain Taylor, resultAgainstBernardHopkinsI, win by split decision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultAgainstBernardHopkinsI Context triple: [Jermain Taylor, resultAgainstBernardHopkinsI, win by split decision]
-
A.
wonChampionshipAgainst
Indicates that one competitor secured a championship title by defeating another specific opponent.
-
B.
defeatedBy
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
-
C.
wonAgainst
chosen
Indicates that one entity achieved victory over another in a competition, conflict, or contest.
-
D.
facedOpponent
Indicates that one entity directly confronted or competed against another as an opponent in a contest, conflict, or challenge.
-
E.
championshipOutcome
Indicates the result or final standing of a competitor or team in a championship event.
- 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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d954b867dc8190af8a70f797e4d133 |
completed | April 10, 2026, 7:51 p.m. |
| PD | Predicate disambiguation | batch_69d954096af88190b6be81b008c82139 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 8, 2026, 9:57 p.m.