Triple
T3381293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U6 |
E71188
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Kochstraße |
E71197
|
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: Kochstraße | Statement: [U6, hasStation, Kochstraße]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kochstraße Context triple: [U6, hasStation, Kochstraße]
-
A.
Kochstraße
chosen
Kochstraße is a Berlin U-Bahn station on line U6 located near Checkpoint Charlie in the central district of Kreuzberg.
-
B.
Deutschland 83
Deutschland 83 is a German Cold War-era television drama series that follows a young East German border guard sent undercover to West Germany as a spy in 1983.
-
C.
Landstraße
Landstraße is Vienna’s 3rd municipal district, a central urban area known for its mix of historic architecture, embassies, and major transport hubs.
-
D.
Bad Tölz
Bad Tölz is a Bavarian spa town in southern Germany known for its historic old town, alpine scenery, and traditional German architecture.
-
E.
Strassenfest
Strassenfest is an annual German-themed street festival in Jasper, Indiana, featuring traditional food, music, parades, and cultural celebrations.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb5e9af608190bfb228ef99a87bb7 |
completed | March 8, 2026, 5:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3344f9b448190aab1038ead60fa48 |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:14 p.m.