Triple
T22058314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marvin Hagler vs. Roberto Durán |
E545080
|
entity |
| Predicate | fighter1Status |
P146453
|
FINISHED |
| Object | reigning undisputed middleweight champion |
—
|
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: reigning undisputed middleweight champion | Statement: [Marvin Hagler vs. Roberto Durán, fighter1Status, reigning undisputed middleweight champion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fighter1Status Context triple: [Marvin Hagler vs. Roberto Durán, fighter1Status, reigning undisputed middleweight champion]
-
A.
fighter1
Indicates that the subject is the first participant or primary combatant in a fight or competitive physical confrontation.
-
B.
fighterNumber
Indicates the identifying number assigned to a fighter within a given context or event.
-
C.
fighter2
Indicates that the subject is the second participant (opponent) in a fighting or combat relationship or event.
-
D.
fighterType
Indicates the specific combat or fighting style category that an entity belongs to.
-
E.
militaryWingStatus
Indicates the status or condition of an entity’s military wing, such as whether it is active, inactive, designated, or otherwise classified.
- 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_69e11e3377c48190890c17407b9527d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1285959f48190b89527b3f9e7ab11 |
completed | April 28, 2026, 9:36 p.m. |
| PD | Predicate disambiguation | batch_69e6f643ca74819083e8ab78e843f243 |
completed | April 21, 2026, 4 a.m. |
| PDg | Predicate description generation | batch_69e6fad4a540819096cdd5ea08527220 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 8:27 p.m.