Triple
T3558919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guillermo Vilas |
E75286
|
entity |
| Predicate | backhandStyle |
P44417
|
FINISHED |
| Object | one-handed backhand |
—
|
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: one-handed backhand | Statement: [Guillermo Vilas, backhandStyle, one-handed backhand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backhandStyle Context triple: [Guillermo Vilas, backhandStyle, one-handed backhand]
-
A.
playsBackhand
chosen
Indicates that an entity performs or executes a backhand stroke or action, typically in a sport such as tennis.
-
B.
battingHand
Indicates the handedness a player uses when batting, such as right-handed, left-handed, or switch.
-
C.
boxingStance
Indicates the specific posture or positioning a boxer adopts while preparing to fight or engage in boxing actions.
-
D.
handicap
Indicates that one entity imposes or experiences a disadvantage, constraint, or limiting condition in relation to another entity or context.
-
E.
styleOfPlay
Indicates the characteristic manner or approach in which an entity performs or behaves, especially in a game, sport, or artistic 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_69ad85d45090819086f34fb85d850a1e |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0881d50819092332491b9527c9d |
completed | March 8, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69adb834779081908468e182d5f6cf02 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:20 p.m.