Triple
T23044728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Messe-Prater |
E573844
|
entity |
| Predicate | adjacentStationOnLineU2 |
P123253
|
FINISHED |
| Object | Praterstern |
—
|
NE NERFINISHED |
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: Praterstern | Statement: [Messe-Prater, adjacentStationOnLineU2, Praterstern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Praterstern Context triple: [Messe-Prater, adjacentStationOnLineU2, Praterstern]
-
A.
Wien Praterstern
chosen
Wien Praterstern is a major railway and transport hub in Vienna, Austria, serving regional, S-Bahn, U-Bahn, tram, and bus lines near the Prater amusement park.
-
B.
Sendlinger Tor
Sendlinger Tor is a historic city gate in Munich, Germany, and one of the remaining medieval entrances to the old town.
-
C.
Kapuzinerberg
Kapuzinerberg is a prominent wooded hill in Salzburg, Austria, known for its historic fortifications, monasteries, and panoramic views over the city.
-
D.
Prater
Prater is a large public park and historic amusement area in Vienna, Austria, best known for its iconic Giant Ferris Wheel and extensive green spaces.
-
E.
Prater
Prater is a surname most notably associated with American soul singer Dave Prater, one half of the duo Sam & Dave.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b9c11481909d06c872214d21af |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1851811e08190a5af6a112687327e |
completed | April 29, 2026, 4:12 a.m. |
Created at: April 17, 2026, 3:54 p.m.