Triple
T22787674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vélizy-Villacoublay |
E564013
|
entity |
| Predicate | hasRoadConnection |
P385
|
FINISHED |
| Object | RN118 |
—
|
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: RN118 | Statement: [Vélizy-Villacoublay, hasRoadConnection, RN118]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RN118 Context triple: [Vélizy-Villacoublay, hasRoadConnection, RN118]
-
A.
R11
R11 is the internal station code used by the New York City Subway for the Grand Central–42nd Street complex in Midtown Manhattan.
-
B.
R11
R11 is a regional railway line in Catalonia, Spain, operating under the Rodalies de Catalunya network and connecting Barcelona with towns toward the French border via Girona and Figueres.
-
C.
RN12
RN12 is a major national road in France that serves as an important route connecting several towns and regions in the western part of the country.
-
D.
N118
chosen
N118 is a national road in France that connects the southwestern suburbs of Paris with the Saclay plateau and surrounding areas.
-
E.
RN193
RN193 is a former French national road designation that was replaced or renumbered as part of the country’s road network reclassification.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c32de6481909ef358d16de98496 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.