Triple
T18096703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hank Williams’ 1952 Cadillac |
E433106
|
entity |
| Predicate | hasLicensePlate |
P42235
|
FINISHED |
| Object | Alabama plate (period-correct) |
—
|
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: Alabama plate (period-correct) | Statement: [Hank Williams’ 1952 Cadillac, hasLicensePlate, Alabama plate (period-correct)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLicensePlate Context triple: [Hank Williams’ 1952 Cadillac, hasLicensePlate, Alabama plate (period-correct)]
-
A.
hasPlate
chosen
Indicates that one entity possesses, is equipped with, or includes a plate as part of its attributes or components.
-
B.
hasLicense
Indicates that an entity possesses a valid authorization or permit, typically granted by an authority, to perform a specific activity or use something.
-
C.
hasVehicleLicensePrefix
Indicates that one entity has, uses, or is associated with a specific vehicle license plate prefix represented by the other entity.
-
D.
licensePlateReference
Indicates a reference or link from one entity to a specific vehicle license plate identifier.
-
E.
isOnLicensePlateBeforeNumber
Indicates that one element appears on a license plate in a position preceding a specified number.
- 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_69d8b907d05c819083cc3bd6021089e6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dd1de6f48190a3fefd02a4b2ab58 |
completed | April 19, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69e4330e1f2881908b2506d47c48736b |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:27 a.m.