Triple
T21372312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geldern |
E527096
|
entity |
| Predicate | connectedByRailTo |
P848
|
FINISHED |
| Object | Kleve |
—
|
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: Kleve | Statement: [Geldern, connectedByRailTo, Kleve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kleve Context triple: [Geldern, connectedByRailTo, Kleve]
-
A.
Kleve
chosen
Kleve is a historic town in western Germany near the Dutch border, known for its medieval castle and role as the former capital of the Duchy of Cleves.
-
B.
Gescher
Gescher is a small town in western Germany’s Münsterland region, noted for its traditional bell foundries and rural character.
-
C.
Gevelsberg
Gevelsberg is a town in North Rhine-Westphalia, Germany, situated in the Ennepe-Ruhr district within the Ruhr metropolitan region.
-
D.
Kreuztal
Kreuztal is a town in the Siegen-Wittgenstein district of North Rhine-Westphalia, Germany, known as an industrial and transport hub in the Siegerland region.
-
E.
Schlettstadt
Schlettstadt, now known as Sélestat, is a historic town in the Alsace region of northeastern France noted for its medieval architecture and humanist heritage.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b0b0d5ec81908da8f38380dbdc7a |
completed | April 22, 2026, 11:27 a.m. |
Created at: April 16, 2026, 5:10 p.m.