Triple
T10541125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TGV Ouigo |
E248696
|
entity |
| Predicate | notableRoute |
P22
|
FINISHED |
| Object | Paris–Bordeaux |
E88046
|
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: Paris–Bordeaux | Statement: [TGV Ouigo, notableRoute, Paris–Bordeaux]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paris–Bordeaux Context triple: [TGV Ouigo, notableRoute, Paris–Bordeaux]
-
A.
Paris–Bordeaux
chosen
Paris–Bordeaux is a major high-speed rail corridor in France connecting the capital with the southwest, known for its fast TGV services.
-
B.
Paris–Toulouse
Paris–Toulouse is a major intercity rail corridor in France linking the capital Paris with the southwestern city of Toulouse.
-
C.
Paris–Clermont-Ferrand
Paris–Clermont-Ferrand is a major French intercity rail route linking the capital Paris with the central city of Clermont-Ferrand.
-
D.
Paris–Côte d’Azur
Paris–Côte d’Azur was a prestigious French express train service linking Paris with the French Riviera, renowned for its luxury and popularity among holiday travelers.
-
E.
Paris–Brest
Paris–Brest is a long-distance French railway service connecting Paris with the city of Brest in Brittany.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a5918648190b16c2d1bc1bf015f |
completed | April 7, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9341d96c08190a6ba644b9acfe2c8 |
completed | April 10, 2026, 5:32 p.m. |
Created at: April 6, 2026, 12:32 p.m.