Triple
T6849446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandy Saddler |
E157977
|
entity |
| Predicate | knockoutRatio |
P66159
|
FINISHED |
| Object | over 70 percent |
—
|
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: over 70 percent | Statement: [Sandy Saddler, knockoutRatio, over 70 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knockoutRatio Context triple: [Sandy Saddler, knockoutRatio, over 70 percent]
-
A.
knockoutNature
Indicates that one entity causes another to be eliminated, disabled, or rendered nonfunctional, typically in a decisive or forceful manner.
-
B.
numberOfKnockouts
Indicates the total count of times an entity has defeated opponents by knockout.
-
C.
recordedKOPercentage
chosen
Indicates the proportion of knockouts (KOs) that has been measured or documented for an entity in a given context.
-
D.
winsByKO
Indicates that one competitor defeats another by knocking them out, ending the contest immediately.
-
E.
eventOfRecordKnockout
Indicates that the event represents a knockout outcome recorded in a competitive match or contest.
- 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_69c6882fae988190864cbba788c5ebb4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d84acb288190a67d974197ecab2f |
completed | March 27, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69c6d0a12834819097d7e6c0b823745e |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:20 p.m.