Triple
T2400154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vennbahn railway |
E47746
|
entity |
| Predicate | passesThrough |
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: [Vennbahn railway, passesThrough, Eupen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eupen Context triple: [Vennbahn railway, passesThrough, 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.
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.
Zottegem
Zottegem is a city and municipality in East Flanders, Belgium, known for its historic center and its role as a regular feature in Flemish cycling races.
-
D.
Binche
Binche is a historic town in the Walloon region of Belgium, renowned for its well-preserved medieval architecture and its UNESCO-recognized Carnival of Binche.
-
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 (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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc8c95d8c819088e4bb4fb32452ae |
completed | March 7, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3737db06481908b854eff532fce18 |
completed | March 13, 2026, 2:16 a.m. |
Created at: March 4, 2026, 7:57 p.m.