Triple
T30142444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torsen center differential |
E766164
|
entity |
| Predicate | canBiasTorque |
P62551
|
FINISHED |
| Object | toward front axle |
—
|
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: toward front axle | Statement: [Torsen center differential, canBiasTorque, toward front axle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBiasTorque Context triple: [Torsen center differential, canBiasTorque, toward front axle]
-
A.
torque
Indicates a rotational force applied by one entity on another around a pivot or axis.
-
B.
torqueDistribution
chosen
Indicates how torque or rotational force is apportioned among multiple components, such as wheels, axles, or motors, within a system.
-
C.
hasRotationMechanic
Indicates that the subject includes or supports a gameplay or functional mechanic involving rotation or turning as a core interaction.
-
D.
leanAngle
Indicates the degree to which an entity is tilted or inclined away from a reference upright position.
-
E.
hasTension
Indicates the presence of strain, stress, or conflict between entities in their relationship or interaction.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67e8982648190b6bfb6b7f8b09d73 |
completed | May 2, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:18 p.m.