Triple
T5035862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaggenau |
E113418
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Kuppenheim |
E418794
|
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: Kuppenheim | Statement: [Gaggenau, hasTwinTown, Kuppenheim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kuppenheim Context triple: [Gaggenau, hasTwinTown, Kuppenheim]
-
A.
Kuppenheim
chosen
Kuppenheim is a small town in the Rastatt district of Baden-Württemberg, southwestern Germany, situated near the Black Forest.
-
B.
Marlenheim
Marlenheim is a commune in northeastern France’s Alsace region, known as a historic wine-producing village and gateway to the area’s renowned vineyards and scenic countryside.
-
C.
Herrenberg
Herrenberg is a historic town in the German state of Baden-Württemberg, known for its well-preserved medieval center and proximity to the Schönbuch Nature Park.
-
D.
Entzheim
Entzheim is a commune in northeastern France, near Strasbourg, best known for hosting Strasbourg Airport.
-
E.
Johannisberg
Johannisberg is a prominent peak in the Austrian Alps, located in the High Tauern range near the Grossglockner.
- 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_69bd44384298819089c49e7c330ec7b8 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73b9ad488190a2a8c4da8858eb91 |
completed | March 20, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfc205d77c8190bcb9e7ce7782202b |
completed | March 22, 2026, 10:18 a.m. |
Created at: March 20, 2026, 1:36 p.m.