Triple
T16387745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U4 line |
E397966
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Innsbrucker Platz |
E410418
|
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: Innsbrucker Platz | Statement: [U4 line, hasStation, Innsbrucker Platz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Innsbrucker Platz Context triple: [U4 line, hasStation, Innsbrucker Platz]
-
A.
Innsbrucker Platz
chosen
Innsbrucker Platz is a public square in Berlin, Germany, known as a local traffic and transport hub in the Schöneberg district.
-
B.
Kagraner Platz
Kagraner Platz is a public square and major transport hub in Vienna’s 22nd district, Donaustadt.
-
C.
Karolinenplatz
Karolinenplatz is a prominent square in central Munich, Germany, known for its circular layout and the Obelisk monument commemorating Bavarian soldiers who died in Napoleon’s Russian campaign.
-
D.
Rosenheimer Platz
Rosenheimer Platz is a central square and transport hub in Munich’s Haidhausen district, known for its busy S-Bahn station and surrounding shops and cafes.
-
E.
Rathausplatz
Rathausplatz is a prominent public square in Vienna, Austria, located in front of the city hall and known for major events such as festivals, markets, and open-air concerts.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e3263e1534819081a6bf5006c611c5 |
completed | April 18, 2026, 6:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c291e2008190b41a989c5c6e2860 |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:08 a.m.