Triple
T23307249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Gracie |
E590482
|
entity |
| Predicate | mmaRecordSummary |
P151050
|
FINISHED |
| Object | 8 wins, 2 losses (professional MMA) |
—
|
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: 8 wins, 2 losses (professional MMA) | Statement: [Roger Gracie, mmaRecordSummary, 8 wins, 2 losses (professional MMA)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mmaRecordSummary Context triple: [Roger Gracie, mmaRecordSummary, 8 wins, 2 losses (professional MMA)]
-
A.
mmaRecord
chosen
Indicates a competitive mixed martial arts fight record between entities, typically summarizing wins, losses, and related bout outcomes.
-
B.
boxingRecordSummary
Indicates the summarized outcome or performance record of an entity in boxing matches, such as total wins, losses, and related statistics.
-
C.
raceRecordSummary
Indicates a summarized record of outcomes or performance across one or more races involving the related entities.
-
D.
careerWinLossRecord
Indicates the overall tally of wins and losses an entity has accumulated over the entire span of its career.
-
E.
mostOverallWinsRecord
Indicates that the subject holds the record for having the greatest total number of wins compared to all others in the relevant context.
- 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1972846fc819092ca2b9590b2e177 |
completed | April 29, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:05 p.m.