Triple
T4458722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Staubach |
E98195
|
entity |
| Predicate | batsOrThrows |
P41780
|
FINISHED |
| Object | throws right-handed |
—
|
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: throws right-handed | Statement: [Roger Staubach, batsOrThrows, throws right-handed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: batsOrThrows Context triple: [Roger Staubach, batsOrThrows, throws right-handed]
-
A.
bats
Indicates that one entity hits or strikes another entity, typically using a bat or similar implement.
-
B.
batsOrThrowsInCollege
Indicates that, in a college sports context, the person’s batting side and/or throwing arm is specified.
-
C.
batsFromSide
chosen
Indicates that one entity performs a batting action from a specified side or orientation (e.g., left-handed or right-handed).
-
D.
batsInOrderTypically
Indicates that one entity typically bats in a specific position or sequence within a batting order relative to others.
-
E.
usesBatAndBall
Indicates that the action or activity involves the use of both a bat and a ball together.
- 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_69b3454a7c608190944f5455c8031d73 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3564485688190a0d49fdccf8724be |
completed | March 13, 2026, 12:11 a.m. |
| PD | Predicate disambiguation | batch_69b34f649df081909d3cc2f6a1b8f282 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:33 p.m.