Triple
T1816909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wassily Kandinsky |
E40454
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Dessau |
E102721
|
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: Dessau | Statement: [Wassily Kandinsky, residence, Dessau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dessau Context triple: [Wassily Kandinsky, residence, Dessau]
-
A.
Dessau
chosen
Dessau is a German city best known for its association with the Bauhaus movement and its iconic modernist architecture.
-
B.
Oranienburg
Oranienburg is a town in Brandenburg, Germany, historically known as the site of the Nazi Sachsenhausen concentration camp.
-
C.
Degendorf
Degendorf is a locality within the Bavarian town and district of Lichtenfels in Germany.
-
D.
Schkopau
Schkopau is a municipality in the Saalekreis district of Saxony-Anhalt, Germany, known for its large chemical industry complex.
-
E.
Lankwitz
Lankwitz is a residential locality in the southwestern part of Berlin, known for its quiet neighborhoods, green spaces, and mix of historic and modern architecture.
- 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_69a8864526c081908a3a4d74f689e2c5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa65f614888190a475f7df627d5f0a |
completed | March 6, 2026, 5:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b0fc189de08190b88849333d824c5b |
completed | March 11, 2026, 5:22 a.m. |
Created at: March 4, 2026, 7:32 p.m.