Triple
T881151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab 96 |
E19028
|
entity |
| Predicate | frontSuspension |
P11929
|
FINISHED |
| Object | double wishbone |
—
|
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: double wishbone | Statement: [Saab 96, frontSuspension, double wishbone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontSuspension Context triple: [Saab 96, frontSuspension, double wishbone]
-
A.
suspensionRear
Indicates that the relationship or action involves the rear suspension component or system of an object, typically a vehicle.
-
B.
suspensionType
chosen
Indicates the specific kind or configuration of suspension system associated with an entity (e.g., a vehicle or structure).
-
C.
suspension
Indicates the temporary removal or halting of a privilege, activity, or status for an entity, often as a consequence or precaution.
-
D.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
E.
partOfFront
Indicates that one entity constitutes a component or section located at the front portion 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_69a4939c32488190a7ccd41cf0abb22b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4accb653c81909fe0753f78145be9 |
completed | March 1, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69a4aa8eca748190b58e0f08b30fba43 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.