Triple
T9601724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | softball |
E231864
|
entity |
| Predicate | pitchingStyleSlowpitch |
P25456
|
FINISHED |
| Object | high-arc underhand pitch |
—
|
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: high-arc underhand pitch | Statement: [softball, pitchingStyleSlowpitch, high-arc underhand pitch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pitchingStyleSlowpitch Context triple: [softball, pitchingStyleSlowpitch, high-arc underhand pitch]
-
A.
pitchingStyle
chosen
Indicates the characteristic manner or technique with which a pitcher delivers the ball.
-
B.
hasPitchType
Indicates that an entity is associated with, or characterized by, a specific type or category of pitch.
-
C.
pitchingDominated
Indicates that one side’s pitching performance overwhelmingly controlled or suppressed the opposing offense.
-
D.
pitcher
Indicates that an entity performs the role of pitching, typically throwing the ball to a batter in a game or similar context.
-
E.
usesPitchingHandedness
Indicates that an entity performs pitching using a specified handedness (e.g., left-handed or right-handed).
- 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_69ca8484838c8190b2049199d22fef70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a3a49608190ad1f65195e4d5cda |
completed | April 1, 2026, 10:20 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a359788190b24f82399489f7fe |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:07 p.m.