Triple
T24765919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcos Maidana |
E619581
|
entity |
| Predicate | resultAgainstAmirKhan |
P158722
|
FINISHED |
| Object | lost by unanimous 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 unanimous decision | Statement: [Marcos Maidana, resultAgainstAmirKhan, lost by unanimous decision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultAgainstAmirKhan Context triple: [Marcos Maidana, resultAgainstAmirKhan, lost by unanimous decision]
-
A.
resultAgainstMuhammadAli
Indicates the outcome or performance of an entity in a contest, match, or comparison specifically against Muhammad Ali.
-
B.
Leon Edwards
Indicates a relationship or context specifically involving Leon Edwards, such as actions performed by him, events centered on him, or associations in which he is a key participant.
-
C.
wonChampionshipAgainst
Indicates that one competitor secured a championship title by defeating another specific opponent.
-
D.
wonFirstRoundAgainst
Indicates that one entity defeated another entity in the first round of a competition, match, or contest.
-
E.
winningBoxer
Indicates that one boxer has defeated another in a boxing match and is recognized as the winner.
- 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_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
| PDg | Predicate description generation | batch_69f48b9058d081908ec9af261ee092e2 |
completed | May 1, 2026, 11:16 a.m. |
Created at: April 18, 2026, 4:28 a.m.