Triple
T17664538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dongducheon |
E440340
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Würzburg, Germany |
—
|
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: Würzburg, Germany | Statement: [Dongducheon, hasSisterCity, Würzburg, Germany]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Würzburg, Germany Context triple: [Dongducheon, hasSisterCity, Würzburg, Germany]
-
A.
Würzburg, Germany
chosen
Würzburg, Germany is a historic city in northern Bavaria known for its baroque and rococo architecture, prominent university, and renowned Franconian wine culture.
-
B.
Saalfeld, Germany
Saalfeld is a historic town in the German state of Thuringia, known for its well-preserved medieval architecture and scenic location on the Saale River.
-
C.
Donauwörth, Germany
Donauwörth, Germany is a Bavarian town on the Danube River known as a regional industrial hub and major site of helicopter production.
-
D.
Herzogenaurach, Germany
Herzogenaurach, Germany is a Bavarian town internationally known as the home base of major sportswear companies Adidas and Puma.
-
E.
Giessen, Germany
Giessen, Germany is a central German university town in the state of Hesse, known for its large student population and academic institutions.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea8accc8190beea0900b0614020 |
completed | April 19, 2026, 5:56 a.m. |
Created at: April 10, 2026, 9:55 a.m.