Triple
T3417132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hallesches Tor |
E72035
|
entity |
| Predicate | adjacentStationOnU3 |
P34401
|
FINISHED |
| Object | Prinzenstraße |
E393134
|
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: Prinzenstraße | Statement: [Hallesches Tor, adjacentStationOnU3, Prinzenstraße]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prinzenstraße Context triple: [Hallesches Tor, adjacentStationOnU3, Prinzenstraße]
-
A.
Prinzenstraße
chosen
Prinzenstraße is a Berlin U-Bahn station on line U1 located in the Kreuzberg district.
-
B.
Yorckstraße
Yorckstraße is a major street and transport corridor in Berlin’s Kreuzberg and Schöneberg districts, known for its multiple S-Bahn stations and proximity to several historic cemeteries and railway viaducts.
-
C.
Kaufingerstraße
Kaufingerstraße is one of Munich’s main and oldest pedestrian shopping streets, lined with stores and historic buildings in the city center.
-
D.
Paradestraße
Paradestraße is a Berlin U-Bahn station on the north–south route in the Tempelhof-Schöneberg district, known for serving the U6 line.
-
E.
Chausseestraße
Chausseestraße is a major historic street in Berlin, Germany, known for its cultural landmarks and central location.
- 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_69ad85ad38e48190b7660c5118a35289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb92c20fc81909b5debced20ec083 |
completed | March 8, 2026, 6 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b511ff137c8190bf9ca22dd71bd205 |
completed | March 14, 2026, 7:45 a.m. |
Created at: March 8, 2026, 3:15 p.m.