Triple
T5553675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bahnhofplatz Zürich |
E145585
|
entity |
| Predicate | connectsWith |
P37
|
FINISHED |
| Object |
Bahnhofstrasse
Bahnhofstrasse is Zürich’s famous luxury shopping street, known for its high-end boutiques, banks, and central location in the city.
|
E536056
|
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: Bahnhofstrasse | Statement: [Bahnhofplatz Zürich, connectsWith, Bahnhofstrasse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bahnhofstrasse Context triple: [Bahnhofplatz Zürich, connectsWith, Bahnhofstrasse]
-
A.
Schaffhauserstrasse
Schaffhauserstrasse is a major street in Zurich, Switzerland, that connects the city center with northern districts and serves as an important urban transport corridor.
-
B.
Winterthurerstrasse
Winterthurerstrasse is a major thoroughfare in Zurich, Switzerland, connecting the city center with its northern districts and the city of Winterthur.
-
C.
Mühlenstrasse
Mühlenstrasse is a street in Berlin, Germany, best known for running alongside the East Side Gallery, the longest remaining section of the Berlin Wall.
-
D.
Hirzelstrasse
Hirzelstrasse is a local road in the Swiss village of Hirzel, serving as one of its main thoroughfares.
-
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: Bahnhofstrasse Triple: [Bahnhofplatz Zürich, connectsWith, Bahnhofstrasse]
Generated description
Bahnhofstrasse is Zürich’s famous luxury shopping street, known for its high-end boutiques, banks, and central location in the city.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bahnhofstrasse Target entity description: Bahnhofstrasse is Zürich’s famous luxury shopping street, known for its high-end boutiques, banks, and central location in the city.
-
A.
Schaffhauserstrasse
Schaffhauserstrasse is a major street in Zurich, Switzerland, that connects the city center with northern districts and serves as an important urban transport corridor.
-
B.
Winterthurerstrasse
Winterthurerstrasse is a major thoroughfare in Zurich, Switzerland, connecting the city center with its northern districts and the city of Winterthur.
-
C.
Mühlenstrasse
Mühlenstrasse is a street in Berlin, Germany, best known for running alongside the East Side Gallery, the longest remaining section of the Berlin Wall.
-
D.
Hirzelstrasse
Hirzelstrasse is a local road in the Swiss village of Hirzel, serving as one of its main thoroughfares.
-
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_69c008fcaf788190bafa02a1917ee73b |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01ff9c9c48190b5e587d58c6515d8 |
completed | March 22, 2026, 4:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04cfc6f808190a39c607f61dcfa32 |
completed | March 22, 2026, 8:11 p.m. |
| NEDg | Description generation | batch_69c04e8422dc8190879ee52bd6850565 |
completed | March 22, 2026, 8:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c04f3963888190b1c85b3bb9ff5d44 |
completed | March 22, 2026, 8:21 p.m. |
Created at: March 22, 2026, 3:35 p.m.