Triple
T12551121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbiadamm |
E300097
|
entity |
| Predicate | hasJunctionWith |
P1018
|
FINISHED |
| Object | Hermannstraße |
E598786
|
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: Hermannstraße | Statement: [Columbiadamm, hasJunctionWith, Hermannstraße]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hermannstraße Context triple: [Columbiadamm, hasJunctionWith, Hermannstraße]
-
A.
Hermannstraße
chosen
Hermannstraße is a Berlin railway and U-Bahn station in the Neukölln district that serves as a key interchange point on the city’s Ringbahn network.
-
B.
Bergmannstraße
Bergmannstraße is a notable street in Berlin, Germany, known for its lively mix of cafés, shops, and historic sites including the Luisenstädtischer Friedhof cemetery.
-
C.
Grunerstraße
Grunerstraße is a central street in Berlin located near Alexanderplatz, known for carrying heavy traffic through the city’s Mitte district.
-
D.
Niederkirchnerstraße
Niederkirchnerstraße is a street in central Berlin, Germany, historically associated with Nazi-era government and security offices and now home to memorial sites such as the Topography of Terror.
-
E.
Hedderichstraße
Hedderichstraße is a street in Frankfurt am Main, Germany, located in the Sachsenhausen district and connected to the city’s public transport network.
- 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_69d6ada707008190aaec1238117c9379 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95482c1348190b6f964decef5cc0a |
completed | April 10, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69b847de481908163d59cc939e132 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 8, 2026, 9:58 p.m.