Triple
T5079204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avelia Liberty |
E114472
|
entity |
| Predicate | hasCab |
P21781
|
FINISHED |
| Object | aerodynamic power car cab ends |
—
|
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: aerodynamic power car cab ends | Statement: [Avelia Liberty, hasCab, aerodynamic power car cab ends]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCab Context triple: [Avelia Liberty, hasCab, aerodynamic power car cab ends]
-
A.
hasControlCab
chosen
Indicates that an entity is equipped with or includes a control cab used for operating or controlling it.
-
B.
hasComb
Indicates that an entity possesses or is equipped with a comb.
-
C.
hasPar
Indicates a relationship where one entity has another entity as its parent.
-
D.
hasCP
Indicates that an entity possesses, is associated with, or is characterized by a specific CP (such as a control point, contact person, or configuration parameter), depending on the domain context.
-
E.
hasStand
Indicates that an entity possesses, is equipped with, or is supported by a stand or base structure.
- 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_69bd443dbf908190a9401e9c2dc7bd7d |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74f75cf0819088be9e076eaf3168 |
completed | March 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69bd7157fe608190b4515d56fdd0a616 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:39 p.m.