Triple
T33956422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moto X Best Trick |
E870582
|
entity |
| Predicate | rampType |
P119068
|
FINISHED |
| Object | metal takeoff ramp |
—
|
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: metal takeoff ramp | Statement: [Moto X Best Trick, rampType, metal takeoff ramp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rampType Context triple: [Moto X Best Trick, rampType, metal takeoff ramp]
-
A.
containsRamps
chosen
Indicates that one entity includes or is equipped with one or more ramps as part of its structure or features.
-
B.
ridgeType
Indicates the specific morphological or structural category that a ridge belongs to within a classification of ridge forms.
-
C.
ratchetType
Indicates the specific mechanism or style of ratcheting action that characterizes how one component moves relative to another.
-
D.
hasRampSpace
Indicates that a location or structure includes designated space for a ramp, allowing sloped access between different levels.
-
E.
slopeType
Indicates the classification of a slope based on its geometric or physical characteristics, such as steepness, shape, or orientation.
- 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_69f3499c2d7481909c953a5010227725 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.