Triple
T12293786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tupolev Tu-154 |
E293031
|
entity |
| Predicate | wingSweep |
P21070
|
FINISHED |
| Object | swept wing |
—
|
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: swept wing | Statement: [Tupolev Tu-154, wingSweep, swept wing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wingSweep Context triple: [Tupolev Tu-154, wingSweep, swept wing]
-
A.
wingSweepAngles
chosen
Indicates the angular positions of an entity’s wings relative to a reference axis, typically describing how far the wings are swept forward or backward.
-
B.
wingConfiguration
Indicates how the wings of an aircraft or creature are arranged or structured relative to its body and to each other.
-
C.
wingFunction
Indicates the functional role or purpose that a wing serves in enabling certain actions or capabilities.
-
D.
wing
Indicates that an entity has a wing or is equipped with wings as a physical feature or structural component.
-
E.
wingOf
Indicates that something is a wing that forms a physical or functional part of 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91d23def88190adbaa282dd03d6c6 |
completed | April 10, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69d91c4ec6c4819085880bdefdd0f354 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.