Triple
T24630983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Association football |
E609672
|
entity |
| Predicate | restartMethodWhenBallCrossesTouchline |
P156826
|
FINISHED |
| Object | throw-in |
—
|
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: throw-in | Statement: [Association football, restartMethodWhenBallCrossesTouchline, throw-in]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restartMethodWhenBallCrossesTouchline Context triple: [Association football, restartMethodWhenBallCrossesTouchline, throw-in]
-
A.
ballOutOfPlayCondition
Indicates that the conditions under which the ball is considered out of play are satisfied.
-
B.
ballReboundPlay
Indicates a play in which the ball bounces or rebounds off a surface or player and continues in active play.
-
C.
ballMustExit
Indicates that the ball is required to leave or move out of a specified area, state, or context.
-
D.
sideOfBall
Indicates the relative position of an entity with respect to a ball, specifying on which side of the ball the entity is located.
-
E.
ballDirection
Indicates the direction in which a ball is or was moving relative to a reference point or frame.
- F. None of above. chosen
Provenance (4 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_69e2c4d1d3708190a0f2dc6a3a8523bb |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be064ff88190b5d9e5ec75a41242 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6d0ab708190b2e3b94dd20ca76b |
completed | April 30, 2026, 12:48 a.m. |
| PDg | Predicate description generation | batch_69f2b8b8bc5881908df49c0b07110246 |
completed | April 30, 2026, 2:04 a.m. |
Created at: April 18, 2026, 2:32 a.m.