Triple
T10045060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Bayonne |
E207594
|
entity |
| Predicate | trainOperator |
P20222
|
FINISHED |
| Object | TGV (SNCF) |
E445505
|
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: TGV (SNCF) | Statement: [Gare de Bayonne, trainOperator, TGV (SNCF)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TGV (SNCF) Context triple: [Gare de Bayonne, trainOperator, TGV (SNCF)]
-
A.
TGV Réseau
TGV Réseau is a later-generation French high-speed trainset used by SNCF, designed for improved performance and comfort on the expanding TGV network.
-
B.
TGV Ouigo
TGV Ouigo is a low-cost high-speed train service operated by SNCF in France, offering budget fares on selected TGV routes.
-
C.
SNCF Connect
SNCF Connect is the official digital platform and app of the French national railway company, providing online ticket booking, travel planning, and real-time information for trains and other transport services.
-
D.
TGV
chosen
TGV is France’s high-speed intercity train service, renowned for rapid connections between major cities such as Paris and Lille.
-
E.
Francorail
Francorail was a French railway manufacturing consortium known for producing high-speed trainsets, including early models of the TGV.
- 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_69ca835ad0608190b7c80b292da004f5 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcf62ecf081909c055171b78a883a |
completed | April 2, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e559a1608190903e9b2dff12bb00 |
completed | April 5, 2026, 10:42 p.m. |
Created at: March 30, 2026, 8:56 p.m.