Triple
T725990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aéroport Charles de Gaulle 2 TGV station |
E14726
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | SNCF |
E37919
|
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: SNCF | Statement: [Aéroport Charles de Gaulle 2 TGV station, operator, SNCF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SNCF Context triple: [Aéroport Charles de Gaulle 2 TGV station, operator, SNCF]
-
A.
SNCF
chosen
SNCF is France’s national state-owned railway company, responsible for operating the country’s passenger and freight rail services and much of its rail infrastructure.
-
B.
SNCF Réseau
SNCF Réseau is the French state-owned rail infrastructure manager responsible for operating, maintaining, and developing France’s national railway network.
-
C.
Intercités
Intercités is a network of French long-distance conventional trains operated by SNCF, connecting major cities and regions across the country.
-
D.
Ouigo
Ouigo is a low-cost high-speed train service operated by France's SNCF, offering budget TGV travel with simplified onboard services.
-
E.
Transilien
Transilien is the suburban and regional rail network operated by SNCF that serves the Île-de-France (Greater Paris) area.
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5a7fb7c819096db848fe2ba246a |
completed | March 1, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a67ef6179c81908e72e3d03b61cca4 |
completed | March 3, 2026, 6:25 a.m. |
Created at: March 1, 2026, 7:37 p.m.