Triple
T8131311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P30 pistol |
E189857
|
entity |
| Predicate | frameFeature |
P26566
|
FINISHED |
| Object | accessory rail |
—
|
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: accessory rail | Statement: [P30 pistol, frameFeature, accessory rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frameFeature Context triple: [P30 pistol, frameFeature, accessory rail]
-
A.
frame
Indicates placing or presenting something within a particular context, structure, or perspective that shapes how it is interpreted.
-
B.
frameType
Indicates the specific structural or categorical kind of frame associated with an entity or relation.
-
C.
frameDevice
chosen
Indicates that one entity serves as a structural or supporting frame for another device or object.
-
D.
sceneFeature
Indicates a characteristic, element, or attribute that is present within or helps define a particular scene.
-
E.
frameWidth
Indicates the measurement of how wide a frame is, typically specifying its horizontal extent or thickness.
- 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_69ca82bcb4848190a9a9d036ad768642 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4c4c2e388190b86854f8b1765e61 |
completed | March 31, 2026, 4:23 a.m. |
| PD | Predicate disambiguation | batch_69cb3696379c8190a20965e59ed8f370 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:34 p.m.