Triple
T3899344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TGV Duplex |
E90446
|
entity |
| Predicate | usedOnService |
P2367
|
FINISHED |
| Object | TGV inOui |
E246182
|
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 inOui | Statement: [TGV Duplex, usedOnService, TGV inOui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TGV inOui Context triple: [TGV Duplex, usedOnService, TGV inOui]
-
A.
TGV inOui
chosen
TGV inOui is SNCF’s premium high-speed train service in France, offering upgraded comfort and amenities on major routes including those served by the LGV Méditerranée line.
-
B.
Bezannes TGV
Bezannes TGV is a tram terminus and transport hub in the suburb of Bezannes serving the high-speed TGV rail connections near Reims, France.
-
C.
TGV Ouigo
TGV Ouigo is a low-cost high-speed train service operated by SNCF in France, offering budget fares on selected TGV routes.
-
D.
TGV Est
TGV Est is a French high-speed train service connecting Paris with eastern France and neighboring European countries such as Germany, Luxembourg, and Switzerland.
-
E.
TGV V150 test train
The TGV V150 test train is a specially modified French high-speed train that set the world rail speed record for conventional trains by reaching 574.8 km/h (357.2 mph) in 2007.
- 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_69aed95d315881908cbf1bf4a7215fbf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecf17ef4819083db0a22e24d5b89 |
completed | March 9, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5d044ec6c81909e2abcb8c429045a |
completed | March 14, 2026, 9:16 p.m. |
Created at: March 9, 2026, 3:21 p.m.