Triple
T811984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab 93 |
E17564
|
entity |
| Predicate | aerodynamicsFeature |
P19885
|
FINISHED |
| Object | streamlined body |
—
|
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: streamlined body | Statement: [Saab 93, aerodynamicsFeature, streamlined body]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aerodynamicsFeature Context triple: [Saab 93, aerodynamicsFeature, streamlined body]
-
A.
wingConfiguration
Indicates how the wings of an aircraft or creature are arranged or structured relative to its body and to each other.
-
B.
wingArea
Indicates the total surface area covered by an entity’s wing or wings.
-
C.
windResistance
Indicates the degree to which an entity opposes or reduces the effect of wind acting upon it.
-
D.
airframe
Indicates that an entity is the structural framework or body of an aircraft associated with another entity (such as a specific model, component, or system).
-
E.
aircraftConfiguration
Indicates the specific arrangement or setup of an aircraft’s components, systems, or features for a given purpose or operating condition.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab4c7418819085cb64c6bf5fa70c |
completed | March 1, 2026, 9:10 p.m. |
| PD | Predicate disambiguation | batch_69a4aa73df08819096d0553a4b2509de |
completed | March 1, 2026, 9:07 p.m. |
| PDg | Predicate description generation | batch_69a4ab4781c88190ae36906251347cdc |
completed | March 1, 2026, 9:10 p.m. |
Created at: March 1, 2026, 7:38 p.m.