Triple
T17308759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friedrichshain-Kreuzberg |
E420234
|
entity |
| Predicate | containsLandmark |
P1098
|
FINISHED |
| Object | Boxhagener Platz |
—
|
NE NERFINISHED |
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: Boxhagener Platz | Statement: [Friedrichshain-Kreuzberg, containsLandmark, Boxhagener Platz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boxhagener Platz Context triple: [Friedrichshain-Kreuzberg, containsLandmark, Boxhagener Platz]
-
A.
Boxhagener Platz
chosen
Boxhagener Platz is a popular square and park in Berlin’s Friedrichshain district, known for its lively weekend flea market, bars, and cafés.
-
B.
Nauener Platz
Nauener Platz is a Berlin U-Bahn station on the U9 line located in the Wedding district of the city.
-
C.
Kaulbachplatz
Kaulbachplatz is an underground station on Munich’s U-Bahn network, serving the U3 line in the Schwabing district.
-
D.
Adenauerplatz
Adenauerplatz is a prominent public square and transport hub in Berlin named after Germany’s first post-war chancellor, Konrad Adenauer.
-
E.
Hermannplatz
Hermannplatz is a major Berlin U-Bahn station and transport hub in the Neukölln district, known for its historic architecture and busy commercial surroundings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43900eca88190930af0e4ec4fc0f9 |
completed | April 19, 2026, 2:08 a.m. |
Created at: April 10, 2026, 5:43 a.m.