Triple
T7369680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vesdre |
E169963
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Eupen |
E300219
|
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: Eupen | Statement: [Vesdre, flowsThrough, Eupen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eupen Context triple: [Vesdre, flowsThrough, Eupen]
-
A.
Eupen
chosen
Eupen is a town in eastern Belgium that serves as the administrative center of the country’s German-speaking Community.
-
B.
Bottendorf
Bottendorf is a locality in the German state of Thuringia that historically existed within the German Empire.
-
C.
Izegem
Izegem is a town in the Belgian province of West Flanders, known historically for its shoe and brush industries.
-
D.
Vilvoorde
Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
-
E.
Durbuy
Durbuy is a small, picturesque town in the Belgian Ardennes often promoted as one of the “smallest cities in the world,” known for its medieval architecture and tourism.
- 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_69c68a5ade988190885b7175f63b7534 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1810668819094aec4b237d08068 |
completed | March 27, 2026, 9:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9de1848108190a0cb612bcbb4119b |
completed | March 30, 2026, 2:21 a.m. |
Created at: March 27, 2026, 3:07 p.m.