Triple
T23085484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | X-47A Pegasus |
E575584
|
entity |
| Predicate | controlSurfaceType |
P21443
|
FINISHED |
| Object | elevons |
—
|
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: elevons | Statement: [X-47A Pegasus, controlSurfaceType, elevons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlSurfaceType Context triple: [X-47A Pegasus, controlSurfaceType, elevons]
-
A.
controlSurfaces
chosen
Indicates that one entity functions as a control surface or set of control surfaces used to influence, steer, or regulate the behavior or state of another entity.
-
B.
controlsType
Indicates that one entity has authority over, or the ability to direct or regulate, the type or category of another entity.
-
C.
controllerShape
Indicates that one entity has the specified geometric or physical form used as a controller in an interaction or system.
-
D.
typeOfControl
Indicates the specific manner or mechanism by which one entity exercises control or influence over another.
-
E.
controlsDeviceType
Indicates that an entity has authority over or can operate a specific type or category of device.
- 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da573588190a8e0c859667e64a6 |
completed | April 29, 2026, 4:48 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:57 p.m.