Triple
T16005731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 3–Roissypôle CDGVAL station |
E388212
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Roissypôle |
E388210
|
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: Roissypôle | Statement: [Terminal 3–Roissypôle CDGVAL station, serves, Roissypôle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roissypôle Context triple: [Terminal 3–Roissypôle CDGVAL station, serves, Roissypôle]
-
A.
Roissypôle
chosen
Roissypôle is a major multimodal transport and business hub located at Paris Charles de Gaulle Airport, integrating train and bus stations with offices, hotels, and services.
-
B.
Ropscha
Ropscha is a rural locality in Leningrad Oblast, Russia, historically known for its imperial estate associated with the Russian royal family.
-
C.
Sapiston
Sapiston is a small rural village located in the English county of Suffolk.
-
D.
Roeser
Roeser is a commune and small town in southern Luxembourg, situated just south of Luxembourg City in the country’s Minett region.
-
E.
Petosega
Petosega is a family name most notably associated with Chief Ignatius Petosega, a historical Indigenous leader.
- 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e157ff33d88190b5a92f7ff70b24eb |
completed | April 16, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffc3dec0c0819099b9007ad0fc6fb4 |
completed | May 9, 2026, 11:31 p.m. |
Created at: April 10, 2026, 4:55 a.m.