Triple
T17920818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kroměříž |
E448060
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Krems an der Donau |
—
|
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: Krems an der Donau | Statement: [Kroměříž, hasTwinTown, Krems an der Donau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krems an der Donau Context triple: [Kroměříž, hasTwinTown, Krems an der Donau]
-
A.
Krems an der Donau
chosen
Krems an der Donau is a historic Austrian city on the Danube River, renowned for its well-preserved medieval old town and its role as a gateway to the Wachau wine region.
-
B.
Tulln an der Donau
Tulln an der Donau is an Austrian town on the Danube River, known for its rich history and as the birthplace of painter Egon Schiele.
-
C.
Wörth an der Donau
Wörth an der Donau is a small Bavarian town on the Danube River in southeastern Germany.
-
D.
Donaustauf
Donaustauf is a market town in Bavaria, Germany, situated on the Danube River just east of the city of Regensburg and known for the nearby Walhalla memorial.
-
E.
Traunkirchen
Traunkirchen is a picturesque lakeside village in Upper Austria, known for its scenic setting on Lake Traunsee and historic pilgrimage church.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.