Triple
T35933176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buchs SG railway station |
E1039221
|
entity |
| Predicate | servesCanton |
P4962
|
FINISHED |
| Object | St. Gallen |
—
|
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: St. Gallen | Statement: [Buchs SG railway station, servesCanton, St. Gallen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesCanton Context triple: [Buchs SG railway station, servesCanton, St. Gallen]
-
A.
hasCanton
chosen
Indicates that an entity is administratively divided into, or associated with, a specific canton.
-
B.
usesCanton
Indicates that one entity employs or applies a specific canton (administrative region or heraldic area) in its structure, context, or operations.
-
C.
operatesInCanton
Indicates that an entity conducts its activities or has operational presence within a specified canton.
-
D.
sourceCanton
Indicates the canton from which something or someone originates or is sourced.
-
E.
denotesCanton
Indicates that one entity is the canton (administrative subdivision) to which another entity belongs or with which it is associated.
- 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_69f76e23e4688190a5369138755138bf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a002ae74da08190a4b47e0ff0f7f8fe |
completed | May 10, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_6a0029cc369c81909578e52c4a75ab18 |
completed | May 10, 2026, 6:46 a.m. |
Created at: May 3, 2026, 4:07 p.m.