Triple
T16089509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line C (Prague Metro) |
E390323
|
entity |
| Predicate | connectsStation |
P845
|
FINISHED |
| Object |
Prosek station
Prosek station is a Prague Metro station on Line C serving the Prosek district in the northeastern part of the city.
|
E1192861
|
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: Prosek station | Statement: [Line C (Prague Metro), connectsStation, Prosek station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prosek station Context triple: [Line C (Prague Metro), connectsStation, Prosek station]
-
A.
Borna station
Borna station is a regional railway station in the town of Borna in Saxony, Germany, serving passenger traffic on the Chemnitz–Leipzig rail corridor.
-
B.
Novza station
Novza station is a metro station on the Tashkent Metro system in Tashkent, Uzbekistan.
-
C.
Bolna Station
Bolna Station is a remote railway stop on Norway’s Nordland Line, serving the mountainous Saltfjellet region just north of the Arctic Circle.
-
D.
Baunatal station
Baunatal station is a Madrid Metro station serving the municipality of San Sebastián de los Reyes in the Community of Madrid, Spain.
-
E.
Zepernick station
Zepernick station is a local railway stop serving the municipality of Panketal in the state of Brandenburg, Germany, as part of the Berlin suburban rail network.
- 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: Prosek station Triple: [Line C (Prague Metro), connectsStation, Prosek station]
Generated description
Prosek station is a Prague Metro station on Line C serving the Prosek district in the northeastern part of the city.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Prosek station Target entity description: Prosek station is a Prague Metro station on Line C serving the Prosek district in the northeastern part of the city.
-
A.
Borna station
Borna station is a regional railway station in the town of Borna in Saxony, Germany, serving passenger traffic on the Chemnitz–Leipzig rail corridor.
-
B.
Novza station
Novza station is a metro station on the Tashkent Metro system in Tashkent, Uzbekistan.
-
C.
Bolna Station
Bolna Station is a remote railway stop on Norway’s Nordland Line, serving the mountainous Saltfjellet region just north of the Arctic Circle.
-
D.
Baunatal station
Baunatal station is a Madrid Metro station serving the municipality of San Sebastián de los Reyes in the Community of Madrid, Spain.
-
E.
Zepernick station
Zepernick station is a local railway stop serving the municipality of Panketal in the state of Brandenburg, Germany, as part of the Berlin suburban rail network.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1845161908190adca2af94710b2cc |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe490d494819081f812811f032702 |
completed | May 10, 2026, 1:51 a.m. |
| NEDg | Description generation | batch_69ffe63f757c81908c7dc3c5ae3075c6 |
completed | May 10, 2026, 1:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffe6b3f25481908dd4b6108b5d95c0 |
completed | May 10, 2026, 2 a.m. |
Created at: April 10, 2026, 4:59 a.m.