Triple
T10128572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gniezno |
E226276
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Velbert |
E740419
|
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: Velbert | Statement: [Gniezno, hasTwinTown, Velbert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Velbert Context triple: [Gniezno, hasTwinTown, Velbert]
-
A.
Velbert
chosen
Velbert is a German city in North Rhine-Westphalia known for its metal and lock manufacturing industry and its location between Düsseldorf, Essen, and Wuppertal.
-
B.
Erkrath
Erkrath is a town in the German state of North Rhine-Westphalia, situated near Düsseldorf in the district of Mettmann.
-
C.
Stadelhofen
Stadelhofen is a village and district of the town of Oberkirch in the Ortenau region of Baden-Württemberg, Germany.
-
D.
Troisdorf
Troisdorf is a town in North Rhine-Westphalia, Germany, located between Cologne and Bonn and known as an important industrial and commuter hub in the Rhine-Sieg district.
-
E.
Walldorf
Walldorf is a town in southwestern Germany best known as the headquarters of software giant SAP and for its strong economic base in the technology sector.
- 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_69ca843057b48190a86730167f5d6b98 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2f0a0e881909267a83fbeb31f0c |
completed | April 2, 2026, 2:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e5c29f6c8190b347a6963ca46dac |
completed | April 5, 2026, 10:44 p.m. |
Created at: March 30, 2026, 9:05 p.m.