Triple
T13248394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A-road |
E315463
|
entity |
| Predicate | designationPrefix |
P70833
|
FINISHED |
| Object | letter A followed by a number |
—
|
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: letter A followed by a number | Statement: [A-road, designationPrefix, letter A followed by a number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designationPrefix Context triple: [A-road, designationPrefix, letter A followed by a number]
-
A.
namePrefix
Indicates that one entity is a prefix or leading part of another entity’s name.
-
B.
designationType
Indicates the specific category or kind of formal status, title, or label that has been assigned in a designation relationship.
-
C.
registrationPrefix
Indicates that an entity has a specific registration prefix code assigned to it as part of its official registration or identification.
-
D.
designationFor
Indicates that one entity serves as the official title, label, or role name assigned to another entity.
-
E.
designationComponent
chosen
Indicates that one entity functions as a component or constituent part of another entity’s designation or formal naming.
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d9e7ea881908abc4b3a54896692 |
completed | April 10, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69d98bcca7d88190a3e68e99ed3a29e6 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:24 p.m.