Triple
T17851523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue Belliard |
E445816
|
entity |
| Predicate | hasNameInDutch |
P13254
|
FINISHED |
| Object | Belliardstraat |
—
|
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: Belliardstraat | Statement: [Rue Belliard, hasNameInDutch, Belliardstraat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Belliardstraat Context triple: [Rue Belliard, hasNameInDutch, Belliardstraat]
-
A.
Belliardstraat
chosen
Belliardstraat is a major street in Brussels, Belgium, running through the European Quarter and lined with numerous EU institutions and office buildings.
-
B.
Valkenburgerstraat
Valkenburgerstraat is a street in central Amsterdam, Netherlands, located near the Waterlooplein area and served by the city’s metro network.
-
C.
Van Baerlestraat
Van Baerlestraat is a major street in Amsterdam known for running alongside the Museumplein and providing access to several prominent museums and cultural institutions.
-
D.
Nijverheidsstraat
Nijverheidsstraat is the Dutch name for Rue de l'Industrie, a street whose name refers to industry or industrial activity.
-
E.
Dapperstraat
Dapperstraat is a well-known shopping and market street in Amsterdam, noted for the daily Dappermarkt and its lively, multicultural atmosphere.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48fff6c288190a2b5e60b66c03ddc |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:17 a.m.