Triple
T6713028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerpen |
E153193
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | St. Vith |
E8397
|
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: St. Vith | Statement: [Kerpen, hasTwinTown, St. Vith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: St. Vith Context triple: [Kerpen, hasTwinTown, St. Vith]
-
A.
St. Vith
chosen
St. Vith is a town in eastern Belgium that became a strategically important battleground during World War II, particularly noted for its role in the Battle of the Bulge.
-
B.
Bastogne
Bastogne is a town in southeastern Belgium best known for its strategic role and fierce fighting during World War II’s Battle of the Bulge.
-
C.
Lannesdorf
Lannesdorf is a residential subdistrict of the Bad Godesberg borough in the city of Bonn, Germany.
-
D.
Beauvechain
Beauvechain is a municipality in Walloon Brabant, Belgium, known for its rural character and the presence of a major Belgian Air Component base.
-
E.
Armentières
Armentières is a commune in northern France near the Belgian border, historically known for its textile industry and World War I significance.
- 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_69c68809b4608190a2509ddb5ab87f05 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d121a92c8190a03f384a8aba84da |
completed | March 27, 2026, 6:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c700948788819087f9b466be337286 |
completed | March 27, 2026, 10:11 p.m. |
Created at: March 27, 2026, 2:07 p.m.