Triple
T23407867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biathlon at the 2018 Winter Olympics |
E559983
|
entity |
| Predicate | shootingPositions |
P134481
|
FINISHED |
| Object | prone |
—
|
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: prone | Statement: [Biathlon at the 2018 Winter Olympics, shootingPositions, prone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shootingPositions Context triple: [Biathlon at the 2018 Winter Olympics, shootingPositions, prone]
-
A.
hasShootingPosition
chosen
Indicates that an entity has a designated location or spot from which shooting (e.g., firing a weapon or taking a shot) is performed.
-
B.
hasShootingLocation
Indicates that an audiovisual work was filmed or recorded at a particular location.
-
C.
shootingRange
Indicates that one entity serves as a location or facility where another entity engages in shooting activities, typically for practice or training.
-
D.
shootingStyle
Indicates the characteristic manner or technique with which an entity performs a shooting action (e.g., in sports or photography).
-
E.
shotBy
Indicates that one entity fired a projectile or weapon that hit and wounded or killed another entity.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50f3f90819084fb682597fee1e1 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:38 p.m.