Triple
T18675729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mechelen railway station |
E456595
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Leuven |
—
|
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: Leuven | Statement: [Mechelen railway station, connectsTo, Leuven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leuven Context triple: [Mechelen railway station, connectsTo, Leuven]
-
A.
Leuven
chosen
Leuven is a historic Belgian city known for hosting KU Leuven, one of Europe’s leading research universities, and for its vibrant academic and cultural life.
-
B.
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.
-
C.
Mechelen
Mechelen is a historic city in the Flemish region of Belgium, known for its rich architectural heritage, medieval center, and prominent role in the Low Countries’ political and religious history.
-
D.
Tervuren
Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
-
E.
Hasselt
Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
- 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_69d8d38f72b4819090a935175d9ca8af |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e556b5a52c81908a71ac86544fb6aa |
completed | April 19, 2026, 10:27 p.m. |
Created at: April 10, 2026, 11:48 a.m.