Triple
T37269280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMW R75 |
E924469
|
entity |
| Predicate | sidecarSuspension |
P11929
|
FINISHED |
| Object | independent suspension |
—
|
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: independent suspension | Statement: [BMW R75, sidecarSuspension, independent suspension]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sidecarSuspension Context triple: [BMW R75, sidecarSuspension, independent suspension]
-
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.
suspensionDevice
Indicates a device or mechanism that supports, hangs, or suspends an object or structure, typically bearing its weight and maintaining its position.
-
D.
suspensionMaterial
Indicates the material from which a suspension (such as a vehicle’s suspension component or system) is made.
-
E.
suspension
Indicates the temporary removal or halting of a privilege, activity, or status for an entity, often as a consequence or precaution.
- 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_69f76eacdd8c819094080d3991e6d37c |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:15 p.m.