Triple
T28779621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First West of England |
E726638
|
entity |
| Predicate | operatesServiceCategory |
P66133
|
FINISHED |
| Object | local bus |
—
|
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: local bus | Statement: [First West of England, operatesServiceCategory, local bus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesServiceCategory Context triple: [First West of England, operatesServiceCategory, local bus]
-
A.
operatesService
Indicates that an agent runs, manages, or provides a particular service.
-
B.
operatesServiceTo
Indicates that one entity runs or provides a transportation or service route to another entity or location.
-
C.
publicServiceCategory
chosen
Indicates the classification or type of public service that an entity, activity, or offering belongs to.
-
D.
operatesBy
Indicates that an entity performs its function, action, or process through the use or application of another entity (e.g., a method, mechanism, or principle).
-
E.
serviceOf
Indicates that one entity performs, provides, or fulfills a function or duty on behalf of another entity.
- 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_69f03199997c8190b6ae43fb19312443 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69fec5c503808190bde0b1829ea43071 |
completed | May 9, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69fec535dd6c8190a6ab85201f5a04a9 |
completed | May 9, 2026, 5:25 a.m. |
Created at: April 28, 2026, 6:19 a.m.