Triple
T6710658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Martin-d’Étampes |
E153130
|
entity |
| Predicate | railwayStationCodeType |
P57454
|
FINISHED |
| Object | SNCF internal code |
—
|
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: SNCF internal code | Statement: [Saint-Martin-d’Étampes, railwayStationCodeType, SNCF internal code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayStationCodeType Context triple: [Saint-Martin-d’Étampes, railwayStationCodeType, SNCF internal code]
-
A.
railwayStationCodeFor
chosen
Indicates that one entity is the designated railway station code corresponding to a particular railway station.
-
B.
railroadCodeFor
Indicates that a specific railroad code is assigned to or used to identify a particular railroad entity.
-
C.
railwayStationFor
Indicates a relationship where a railway station serves, is designated for, or primarily associated with a particular place, line, or service.
-
D.
railwayStationCategory
Indicates the classification or type category assigned to a railway station within a rail network or system.
-
E.
networkRailRouteCode
Indicates that a specific Network Rail route code is assigned to or associated with an entity, identifying the rail route it belongs to or operates on.
- 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_69c68808d8d8819087369015270788fe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d121a92c8190a03f384a8aba84da |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:06 p.m.