Triple
T7803486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hackescher Markt |
E180488
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Museumsinsel |
E108790
|
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: Museumsinsel | Statement: [Hackescher Markt, near, Museumsinsel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Museumsinsel Context triple: [Hackescher Markt, near, Museumsinsel]
-
A.
Museum Island
chosen
Museum Island is a UNESCO World Heritage–listed complex of renowned museums on an island in central Berlin, Germany.
-
B.
Tiergarten
Tiergarten is a large central park in Berlin known for its expansive green spaces, monuments, and cultural landmarks.
-
C.
Schlossinsel Köpenick
Schlossinsel Köpenick is a historic island in Berlin’s Köpenick district, best known for its baroque Köpenick Palace and scenic location where the Dahme and Spree rivers meet.
-
D.
Museumsinsel in Munich
Museumsinsel in Munich is a river island in the Isar best known as the site of the Deutsches Museum, one of the world’s largest science and technology museums.
-
E.
Luisenpark
Luisenpark is a large, historic urban park in Mannheim, Germany, known for its landscaped gardens, lakes, zoo areas, and recreational facilities.
- 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_69ca827e50cc8190a92a733577184938 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf635a4648190af907a686d87f073 |
completed | March 30, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5a2fd718819097cee2482bca74ad |
completed | March 31, 2026, 5:22 a.m. |
Created at: March 30, 2026, 4:34 p.m.