Triple
T4986713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ÖBB |
E112020
|
entity |
| Predicate | secondaryHub |
P8522
|
FINISHED |
| Object |
Salzburg Hauptbahnhof
Salzburg Hauptbahnhof is the main railway station in Salzburg, Austria, serving as a major national and international transport hub.
|
E486905
|
NE FINISHED |
How this triple was built (4 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: Salzburg Hauptbahnhof | Statement: [ÖBB, secondaryHub, Salzburg Hauptbahnhof]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salzburg Hauptbahnhof Context triple: [ÖBB, secondaryHub, Salzburg Hauptbahnhof]
-
A.
Innsbruck Hauptbahnhof
Innsbruck Hauptbahnhof is the main railway station and central transport hub of Innsbruck, Austria, serving regional, national, and international train connections.
-
B.
Graz Hauptbahnhof
Graz Hauptbahnhof is the main railway station and central transport hub of the city of Graz in Austria.
-
C.
Linz Central Station
Linz Central Station is the main railway hub of Linz, Austria, serving as a key regional and long-distance transport interchange.
-
D.
Wien Hauptbahnhof
Wien Hauptbahnhof is Vienna’s main railway station and a central national and international transport hub in Austria.
-
E.
Vienna station
Vienna station is a Washington Metro rapid transit station in Fairfax County, Virginia, serving as the western endpoint of the system’s Orange Line.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Salzburg Hauptbahnhof Triple: [ÖBB, secondaryHub, Salzburg Hauptbahnhof]
Generated description
Salzburg Hauptbahnhof is the main railway station in Salzburg, Austria, serving as a major national and international transport hub.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Salzburg Hauptbahnhof Target entity description: Salzburg Hauptbahnhof is the main railway station in Salzburg, Austria, serving as a major national and international transport hub.
-
A.
Innsbruck Hauptbahnhof
Innsbruck Hauptbahnhof is the main railway station and central transport hub of Innsbruck, Austria, serving regional, national, and international train connections.
-
B.
Graz Hauptbahnhof
Graz Hauptbahnhof is the main railway station and central transport hub of the city of Graz in Austria.
-
C.
Linz Central Station
Linz Central Station is the main railway hub of Linz, Austria, serving as a key regional and long-distance transport interchange.
-
D.
Wien Hauptbahnhof
Wien Hauptbahnhof is Vienna’s main railway station and a central national and international transport hub in Austria.
-
E.
Vienna station
Vienna station is a Washington Metro rapid transit station in Fairfax County, Virginia, serving as the western endpoint of the system’s Orange Line.
- F. None of above. chosen
Provenance (5 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_69bd441be7bc8190b530362d427b97d2 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd727c25bc8190b72f6ddd3772c80a |
completed | March 20, 2026, 4:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be924f11c88190abe6263bf11b848c |
completed | March 21, 2026, 12:42 p.m. |
| NEDg | Description generation | batch_69be94a54fac8190b11cad5e6258536c |
completed | March 21, 2026, 12:52 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69be950871cc819091e6b2eabaa0ecc7 |
completed | March 21, 2026, 12:54 p.m. |
Created at: March 20, 2026, 1:34 p.m.