Triple
T17840329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TGV |
E445505
|
entity |
| Predicate | route |
P5619
|
FINISHED |
| Object | Lyon–Marseille |
—
|
NE NERFINISHED |
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: Lyon–Marseille | Statement: [TGV, route, Lyon–Marseille]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyon–Marseille Context triple: [TGV, route, Lyon–Marseille]
-
A.
Paris–Montpellier
Paris–Montpellier is a major high-speed rail corridor in France linking the capital with the Mediterranean city of Montpellier.
-
B.
Lyon–Marseille axis
chosen
The Lyon–Marseille axis is a major French railway corridor linking the cities of Lyon and Marseille and serving as a key north–south route in southeastern France.
-
C.
Bordeaux-Talence
Bordeaux-Talence is a campus location of the French engineering grande école Arts et Métiers, situated in the Bordeaux metropolitan area.
-
D.
Derby de la Côte d’Azur
The Derby de la Côte d’Azur is a French Riviera football rivalry match, most notably contested between AS Monaco FC and OGC Nice.
-
E.
Toulon
Toulon is a major port city on France’s Mediterranean coast that serves as the principal base of the French Navy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d2b2ea08190926ec0cf01285833 |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:16 a.m.