Triple
T4190012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HD |
E89010
|
entity |
| Predicate | vehicleRegistrationSystem |
P18660
|
FINISHED |
| Object | German vehicle registration plate system |
—
|
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: German vehicle registration plate system | Statement: [HD, vehicleRegistrationSystem, German vehicle registration plate system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vehicleRegistrationSystem Context triple: [HD, vehicleRegistrationSystem, German vehicle registration plate system]
-
A.
vehicleRegistrationCode
Indicates the official registration identifier assigned to a vehicle, typically used for legal identification and record-keeping.
-
B.
registrationNumber
Indicates the unique identifier assigned to an entity as part of an official or formal registration process.
-
C.
identifiesVehiclesRegisteredIn
Indicates that an entity specifies or determines which vehicles are registered within a particular scope or authority.
-
D.
licensePlateSystem
chosen
Indicates a system or scheme used to assign, format, and manage license plate identifiers for vehicles.
-
E.
vehicleUsed
Indicates that a particular vehicle is utilized or employed in performing an action, event, or activity.
- 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_69aed9569a4481908b6c1fcec2a11e21 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af04b009dc8190abda3f149a5b16fa |
completed | March 9, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69af01935064819096b7619f42e164dd |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:46 p.m.