Triple
T25739055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Hearns vs Roberto Durán (1984) |
E648162
|
entity |
| Predicate | fighter2StatusEnteringBout |
P158737
|
FINISHED |
| Object | former 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: former middleweight champion | Statement: [Thomas Hearns vs Roberto Durán (1984), fighter2StatusEnteringBout, former middleweight champion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fighter2StatusEnteringBout Context triple: [Thomas Hearns vs Roberto Durán (1984), fighter2StatusEnteringBout, former middleweight champion]
-
A.
fighter2StatusBeforeFight
chosen
Indicates the condition or state of the second fighter immediately prior to the fight.
-
B.
fighter1StatusBeforeFight
Indicates the condition or state of the first fighter immediately prior to the start of the fight.
-
C.
fighter2Status
Indicates the current condition or state of the second fighter in a combat or competitive context.
-
D.
fighter1Status
Indicates the current condition or state of the first fighter in a combat or competitive context.
-
E.
fighter2RecordBeforeFight
Indicates the win-loss-draw record of the second fighter as it stood immediately before the specified fight.
- 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_69e7ab306eec8190b05c312c6ab186b8 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 22, 2026, 3:39 a.m.