Triple
T35808840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punt Kick |
E1035173
|
entity |
| Predicate | typicalCameraShot |
P206063
|
FINISHED |
| Object | close-up on impact |
—
|
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: close-up on impact | Statement: [Punt Kick, typicalCameraShot, close-up on impact]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalCameraShot Context triple: [Punt Kick, typicalCameraShot, close-up on impact]
-
A.
typicalCameraPlacement
Indicates the usual or standard spatial position where a camera is placed relative to a scene or subject.
-
B.
typicalStillType
Indicates that something represents the usual or characteristic form, style, or configuration that an entity typically has or uses.
-
C.
shotIn
Indicates that an event, scene, or media production was filmed or recorded at a particular location.
-
D.
shotOn
Indicates that one entity fired or took a shot at another entity, typically in a sports or combat context.
-
E.
shotFrom
Indicates that something is propelled or discharged starting at a particular source or origin.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037ce70f54819082946dad8d380825 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a037a069e6c8190857b611fffb7b867 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037ce53de881908cf14141cf3bc570 |
completed | May 12, 2026, 7:17 p.m. |
Created at: May 3, 2026, 4:06 p.m.