Triple
T11926151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Nantes railway |
E283786
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Nantes station |
E108824
|
NE 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: Nantes station | Statement: [Paris–Nantes railway, connectsTo, Nantes station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nantes station Context triple: [Paris–Nantes railway, connectsTo, Nantes station]
-
A.
Gare de Nantes
chosen
Gare de Nantes is the main railway station serving the city of Nantes in western France, providing regional and high-speed train connections.
-
B.
Clermont-Ferrand station
Clermont-Ferrand station is the main railway station serving the city of Clermont-Ferrand in central France, acting as a key regional hub for passenger rail services.
-
C.
Lyon station
Lyon station is an underground light rail transit station in downtown Ottawa, Canada, serving the city’s O-Train Confederation Line.
-
D.
Bordeaux-Saint-Jean station
Bordeaux-Saint-Jean station is the main railway hub of Bordeaux in southwestern France, serving as a major high-speed and regional train interchange on the national rail network.
-
E.
Troyes station
Troyes station is the main railway station serving the city of Troyes in northeastern France, providing regional and intercity train connections.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab2ce9c48190b5d39511b524f666 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e8e3ff308190851ce656286bc67e |
completed | April 10, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f458a576fc8190b68b27365cd53caf |
completed | May 1, 2026, 7:39 a.m. |
Created at: April 8, 2026, 9:45 p.m.