Triple
T38556920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edinburgh Gateway station |
E925271
|
entity |
| Predicate | hasPlatformConnection |
P86957
|
FINISHED |
| Object | rail platforms |
—
|
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: rail platforms | Statement: [Edinburgh Gateway station, hasPlatformConnection, rail platforms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlatformConnection Context triple: [Edinburgh Gateway station, hasPlatformConnection, rail platforms]
-
A.
hasPlatformsConnectedBy
chosen
Indicates that two or more platforms are linked together by some connecting structure or mechanism.
-
B.
hasConnection
Indicates that there exists a link, association, or relationship between two entities.
-
C.
hasModeConnection
Indicates a relationship where one entity is linked to another through a specific mode, method, or type of connection.
-
D.
hasSurfaceConnection
Indicates that two entities are directly connected or in contact at their surfaces, allowing interaction or continuity between them.
-
E.
hasPlatformContext
Indicates that something exists or operates within a specific platform environment, configuration, or contextual setting.
- 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe78e545888190a239af1a84280fa0 |
completed | May 8, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69fe7842742081908043eb950ed69f92 |
completed | May 8, 2026, 11:56 p.m. |
Created at: May 3, 2026, 4:32 p.m.