Triple
T22183649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vienna U-Bahn line U3 |
E548234
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Johnstraße
Johnstraße is a Vienna U-Bahn station on line U3 serving the Rudolfsheim-Fünfhaus district in western Vienna.
|
E1528173
|
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: Johnstraße | Statement: [Vienna U-Bahn line U3, hasStation, Johnstraße]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johnstraße Context triple: [Vienna U-Bahn line U3, hasStation, Johnstraße]
-
A.
Berliner Straße
Berliner Straße is a major Berlin U-Bahn station complex in the district of Wilmersdorf, serving as a key transfer point between multiple subway lines.
-
B.
Berliner Straße
Berliner Straße is a central street in the historic city of Görlitz, Germany, known for its traditional urban architecture and role as a key thoroughfare near the Obermarkt.
-
C.
Perusastraße
Perusastraße is a street in central Munich, Germany, located near Odeonsplatz in the historic city center.
-
D.
Frankfurter Allee
Frankfurter Allee is a major street and transport hub in Berlin, Germany, served by both U-Bahn and S-Bahn lines.
-
E.
Luxemburger Straße
Luxemburger Straße is a street located near Leopoldplatz in Berlin, Germany.
- 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: Johnstraße Triple: [Vienna U-Bahn line U3, hasStation, Johnstraße]
Generated description
Johnstraße is a Vienna U-Bahn station on line U3 serving the Rudolfsheim-Fünfhaus district in western Vienna.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Johnstraße Target entity description: Johnstraße is a Vienna U-Bahn station on line U3 serving the Rudolfsheim-Fünfhaus district in western Vienna.
-
A.
Berliner Straße
Berliner Straße is a major Berlin U-Bahn station complex in the district of Wilmersdorf, serving as a key transfer point between multiple subway lines.
-
B.
Berliner Straße
Berliner Straße is a central street in the historic city of Görlitz, Germany, known for its traditional urban architecture and role as a key thoroughfare near the Obermarkt.
-
C.
Perusastraße
Perusastraße is a street in central Munich, Germany, located near Odeonsplatz in the historic city center.
-
D.
Frankfurter Allee
Frankfurter Allee is a major street and transport hub in Berlin, Germany, served by both U-Bahn and S-Bahn lines.
-
E.
Luxemburger Straße
Luxemburger Straße is a street located near Leopoldplatz in Berlin, Germany.
- 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aa75440819084cbe9176b9edb47 |
completed | April 28, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0abc9178608190a74d2aadc999eec9 |
completed | May 18, 2026, 7:15 a.m. |
| NEDg | Description generation | batch_6a0abd25b4fc8190ad3f51f9a9ad9672 |
completed | May 18, 2026, 7:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0abd9e324481908acad3484a5701ba |
completed | May 18, 2026, 7:19 a.m. |
Created at: April 16, 2026, 8:35 p.m.