Triple
T8880136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue de Saint-Quentin |
E211387
|
entity |
| Predicate | hasTransportConnection |
P845
|
FINISHED |
| Object | RER |
E68667
|
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: RER | Statement: [Rue de Saint-Quentin, hasTransportConnection, RER]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RER Context triple: [Rue de Saint-Quentin, hasTransportConnection, RER]
-
A.
RER D
RER D is one of the main lines of the Paris regional express network (RER), connecting northern and southern suburbs through central Paris.
-
B.
RER C
RER C is a major line of the Paris regional express rail network that connects central Paris with several suburbs and key destinations, including access to Orly Airport.
-
C.
RER network
chosen
The RER network is a rapid transit system of express suburban trains serving Paris and its surrounding metropolitan area, integrating both urban and regional rail services.
-
D.
RER A terminus
RER A terminus is the endpoint station of Paris’s RER A commuter rail line, where trains start or finish their routes.
-
E.
RER A
RER A is one of the main lines of the Paris regional express network, carrying large volumes of commuters and travelers between central Paris and its suburbs.
- 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61677c9c8190aa09dc2a05d4cf95 |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfabc1992481909e8a4216086d5111 |
completed | April 3, 2026, noon |
Created at: March 30, 2026, 6:52 p.m.