Triple
T14446020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Havel |
E358205
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
Schwanenwerder
Schwanenwerder is a small, affluent island neighborhood in southwestern Berlin, known for its exclusive villas and scenic location in the River Havel.
|
E1099565
|
NE FINISHED |
How this triple was built (4 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: Schwanenwerder | Statement: [River Havel, hasIsland, Schwanenwerder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schwanenwerder Context triple: [River Havel, hasIsland, Schwanenwerder]
-
A.
Birkenwerder
Birkenwerder is a small municipality in the German state of Brandenburg, located just north of Berlin and known for its residential character and surrounding forests.
-
B.
Marienfelde
Marienfelde is a locality in the southern part of Berlin known for its residential areas and historical refugee reception center.
-
C.
Falkensee
Falkensee is a town in the Havelland district of Brandenburg, Germany, situated just west of Berlin and functioning largely as a residential suburb of the capital.
-
D.
Hasselwerder
Hasselwerder is a small island located in Lake Tegel in Berlin, Germany.
-
E.
Grevesmühlen
Grevesmühlen is a small town in the German state of Mecklenburg-Vorpommern, known as a local administrative and service center in the north of the country.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Schwanenwerder Triple: [River Havel, hasIsland, Schwanenwerder]
Generated description
Schwanenwerder is a small, affluent island neighborhood in southwestern Berlin, known for its exclusive villas and scenic location in the River Havel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Schwanenwerder Target entity description: Schwanenwerder is a small, affluent island neighborhood in southwestern Berlin, known for its exclusive villas and scenic location in the River Havel.
-
A.
Birkenwerder
Birkenwerder is a small municipality in the German state of Brandenburg, located just north of Berlin and known for its residential character and surrounding forests.
-
B.
Marienfelde
Marienfelde is a locality in the southern part of Berlin known for its residential areas and historical refugee reception center.
-
C.
Falkensee
Falkensee is a town in the Havelland district of Brandenburg, Germany, situated just west of Berlin and functioning largely as a residential suburb of the capital.
-
D.
Hasselwerder
Hasselwerder is a small island located in Lake Tegel in Berlin, Germany.
-
E.
Grevesmühlen
Grevesmühlen is a small town in the German state of Mecklenburg-Vorpommern, known as a local administrative and service center in the north of the country.
- F. None of above. chosen
Provenance (5 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_69d82794dfa081909b9134ad2e32244b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de915e76f481909fe9462f964b5b1c |
completed | April 14, 2026, 7:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bdd0f388190870ddd01f66d3e99 |
completed | May 8, 2026, 3:43 a.m. |
| NEDg | Description generation | batch_69fd5e188a148190bb166b7d50ad3b46 |
completed | May 8, 2026, 3:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd5ea592cc8190a47a2f6a511c0549 |
completed | May 8, 2026, 3:55 a.m. |
Created at: April 10, 2026, 1:19 a.m.