Triple
T14927817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirehampton railway station |
E372176
|
entity |
| Predicate | hasOperatorClass |
P83225
|
FINISHED |
| Object | National Rail station |
—
|
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: National Rail station | Statement: [Shirehampton railway station, hasOperatorClass, National Rail station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOperatorClass Context triple: [Shirehampton railway station, hasOperatorClass, National Rail station]
-
A.
operatorClass
chosen
Indicates the classification or category of an operator in terms of its type, role, or functional group within a system or domain.
-
B.
isOperatorOn
Indicates that one entity serves as an operator responsible for operating, controlling, or managing another entity (such as a system, machine, or process).
-
C.
hasMajorOperator
Indicates that an entity is primarily operated, managed, or run by a specified main operator or organization.
-
D.
involvesOperator
Indicates that a given process, action, or relationship includes or makes use of a specific operator as a participating element.
-
E.
hasOriginalOperator
Indicates that an entity is associated with the operator that originally created, owned, or controlled it.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded634e67881909daec9eaef188d09 |
completed | April 15, 2026, 12:05 a.m. |
| PD | Predicate disambiguation | batch_69de9a52ba988190a26e268b4ea083ea |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:35 a.m.