Triple
T36909066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gleneagles railway station |
E912856
|
entity |
| Predicate | railwayCompanyHistoric |
P5620
|
FINISHED |
| Object | Caledonian Railway |
—
|
NE NERFINISHED |
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: Caledonian Railway | Statement: [Gleneagles railway station, railwayCompanyHistoric, Caledonian Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayCompanyHistoric Context triple: [Gleneagles railway station, railwayCompanyHistoric, Caledonian Railway]
-
A.
railwayCompany
chosen
Indicates that one entity is a railway company that owns, operates, or manages railway services or infrastructure in relation to another entity.
-
B.
railwayHeritageFrom
Indicates that something derives its historical or cultural significance from a particular railway or railway-related source.
-
C.
laterRailwayCompany
Indicates that one railway company is the successor or later incarnation of another railway company.
-
D.
heritageRailwayName
Indicates the specific name assigned to a heritage railway associated with an entity.
-
E.
railwayCompanyContext
Indicates a contextual relationship where an entity is considered or interpreted specifically in its role or capacity as a railway company.
- 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_69f76e879768819085c2fb31a6a5b44b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcc7338120819081cb46547d60f2cb |
completed | May 7, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
Created at: May 3, 2026, 4:13 p.m.