Triple
T24765920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcos Maidana |
E619581
|
entity |
| Predicate | resultAgainstFloydMayweatherJrI |
P159035
|
FINISHED |
| Object | lost by majority 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: lost by majority decision | Statement: [Marcos Maidana, resultAgainstFloydMayweatherJrI, lost by majority decision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultAgainstFloydMayweatherJrI Context triple: [Marcos Maidana, resultAgainstFloydMayweatherJrI, lost by majority decision]
-
A.
resultAgainstAmirKhan
Indicates the outcome or performance of an entity in a contest, match, or event specifically when competing against Amir Khan.
-
B.
resultAgainstMuhammadAli
Indicates the outcome or performance of an entity in a contest, match, or comparison specifically against Muhammad Ali.
-
C.
wonChampionshipAgainst
Indicates that one competitor secured a championship title by defeating another specific opponent.
-
D.
fightNumberForFrazier
Indicates the specific fight number or sequence position of a bout involving Frazier within a series of fights.
-
E.
numberOfFightsWithMannyPacquiao
Indicates the count of distinct fights an entity has had against Manny Pacquiao.
- F. None of above. chosen
Provenance (4 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_69e2fabbea94819092ed41348909622f |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
| PDg | Predicate description generation | batch_69f497b8abb88190bb672cf6907c4b8d |
completed | May 1, 2026, 12:08 p.m. |
Created at: April 18, 2026, 4:28 a.m.