Triple
T16050777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U-Bahnhof Schloßstraße |
E389345
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | U9 Schloßstraße |
E353649
|
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: U9 Schloßstraße | Statement: [U-Bahnhof Schloßstraße, hasStationCode, U9 Schloßstraße]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: U9 Schloßstraße Context triple: [U-Bahnhof Schloßstraße, hasStationCode, U9 Schloßstraße]
-
A.
U9
U9 is a line of the Frankfurt U-Bahn rapid transit network serving parts of Frankfurt am Main, Germany.
-
B.
U9
chosen
U9 is a Berlin U-Bahn subway line that serves the Wedding district among other areas in the city.
-
C.
U9
U9 is a line of the Stuttgart Stadtbahn light rail network serving various districts within the Stuttgart metropolitan area.
-
D.
Frankfurt U9
Frankfurt U9 is a line of the Frankfurt U-Bahn rapid transit network in Frankfurt am Main, Germany.
-
E.
U5/U6 Unter den Linden
U5/U6 Unter den Linden is the central Berlin U-Bahn station where the U5 and U6 lines intersect beneath the historic Unter den Linden boulevard near the city’s main landmarks.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18361c31481908b253e8b814ec9f6 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbe095908190ba10399ad6f3b5f8 |
completed | May 10, 2026, 1:14 a.m. |
Created at: April 10, 2026, 4:56 a.m.