Triple
T3526787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Otto Dix |
E74557
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Prager Strasse
Prager Strasse is a famous 1920s painting by German artist Otto Dix that depicts the chaotic, fractured life of post–World War I urban Germany.
|
E415345
|
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: Prager Strasse | Statement: [Otto Dix, notableWork, Prager Strasse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prager Strasse Context triple: [Otto Dix, notableWork, Prager Strasse]
-
A.
Paradestraße
Paradestraße is a Berlin U-Bahn station on the north–south route in the Tempelhof-Schöneberg district, known for serving the U6 line.
-
B.
Luxemburger Straße
Luxemburger Straße is a street located near Leopoldplatz in Berlin, Germany.
-
C.
Leipziger Straße
Leipziger Straße is a major historic thoroughfare in central Berlin, known for its government buildings, commercial centers, and role in the city’s urban core.
-
D.
Herbertstraße
Herbertstraße is a short, gated street in Hamburg’s St. Pauli district known as one of Germany’s most famous red-light prostitution streets.
-
E.
Gerichtstraße
Gerichtstraße is a street in Berlin, Germany, located in the Wedding district and known for its mix of residential buildings, commercial spaces, and cultural venues.
- 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: Prager Strasse Triple: [Otto Dix, notableWork, Prager Strasse]
Generated description
Prager Strasse is a famous 1920s painting by German artist Otto Dix that depicts the chaotic, fractured life of post–World War I urban Germany.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Prager Strasse Target entity description: Prager Strasse is a famous 1920s painting by German artist Otto Dix that depicts the chaotic, fractured life of post–World War I urban Germany.
-
A.
Paradestraße
Paradestraße is a Berlin U-Bahn station on the north–south route in the Tempelhof-Schöneberg district, known for serving the U6 line.
-
B.
Luxemburger Straße
Luxemburger Straße is a street located near Leopoldplatz in Berlin, Germany.
-
C.
Leipziger Straße
Leipziger Straße is a major historic thoroughfare in central Berlin, known for its government buildings, commercial centers, and role in the city’s urban core.
-
D.
Herbertstraße
Herbertstraße is a short, gated street in Hamburg’s St. Pauli district known as one of Germany’s most famous red-light prostitution streets.
-
E.
Gerichtstraße
Gerichtstraße is a street in Berlin, Germany, located in the Wedding district and known for its mix of residential buildings, commercial spaces, and cultural venues.
- 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_69ad85d0c5488190a3d8e02ebd01a1aa |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc6bb0748190bfccfe25d2ab41b7 |
completed | March 8, 2026, 6:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5767842bc8190849c79a510160654 |
completed | March 14, 2026, 2:53 p.m. |
| NEDg | Description generation | batch_69b57729ca3881909be016ad92a65785 |
completed | March 14, 2026, 2:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5778dcdc08190aee087f6d54992dc |
completed | March 14, 2026, 2:58 p.m. |
Created at: March 8, 2026, 3:19 p.m.