Triple
T4003349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wesel |
E89464
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Salzwedel |
E385908
|
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: Salzwedel | Statement: [Wesel, hasTwinTown, Salzwedel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salzwedel Context triple: [Wesel, hasTwinTown, Salzwedel]
-
A.
Salzwedel
chosen
Salzwedel is a historic town in the German state of Saxony-Anhalt, known for its medieval architecture and as the birthplace of Jenny von Westphalen, the wife of Karl Marx.
-
B.
Zerbst
Zerbst is a historic town in Saxony-Anhalt, Germany, known as the birthplace of Catherine the Great and for its former role as a princely residence.
-
C.
Fürstenwalde
Fürstenwalde is a town in eastern Germany’s Brandenburg region, known for its location on the River Spree and its historic churches and medieval architecture.
-
D.
Seligenstadt
Seligenstadt is a historic town in Hesse, Germany, known for its well-preserved medieval center and its association with the Carolingian scholar Einhard.
-
E.
Hasselwerder
Hasselwerder is a small island located in Lake Tegel in Berlin, Germany.
- 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_69aed9585e788190bec2d39deba3750f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa5de98c8190a95b21a75fffdef3 |
completed | March 9, 2026, 4:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be6f845ce48190a5feae21980530d6 |
completed | March 21, 2026, 10:14 a.m. |
Created at: March 9, 2026, 3:34 p.m.