Triple
T26850193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strathspey Railway |
E676035
|
entity |
| Predicate | originalOperatorOfLine |
P46946
|
FINISHED |
| Object | Highland 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: Highland Railway | Statement: [Strathspey Railway, originalOperatorOfLine, Highland Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalOperatorOfLine Context triple: [Strathspey Railway, originalOperatorOfLine, Highland Railway]
-
A.
initialOperator
Indicates that an entity serves as the first or primary operator initiating a process, action, or operation involving another entity.
-
B.
originalLine
Indicates that one entity is the initial or source version of a line from which other versions or derivatives may originate.
-
C.
hasOriginalOperator
chosen
Indicates that an entity is associated with the operator that originally created, owned, or controlled it.
-
D.
lineOpeningOperator
Indicates that an operator is responsible for initiating or opening a line, such as a production line, communication line, or service line.
-
E.
associatedLineOperator
Indicates that an entity is linked to, managed by, or otherwise connected with a specific line operator.
- 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_69eee9b9d7708190a15d7485709ae981 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: April 27, 2026, 5:16 a.m.