Triple
T16089524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line C (Prague Metro) |
E390323
|
entity |
| Predicate | connectsStation |
P845
|
FINISHED |
| Object |
Roztyly station
Roztyly station is a Prague Metro station on Line C located in the southern part of the city, serving the Roztyly district and nearby residential and commercial areas.
|
E1200056
|
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: Roztyly station | Statement: [Line C (Prague Metro), connectsStation, Roztyly station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roztyly station Context triple: [Line C (Prague Metro), connectsStation, Roztyly station]
-
A.
Letňany station
Letňany station is a Prague Metro station in the Letňany district that serves as the northern terminus of Line C.
-
B.
Ládví station
Ládví station is a Prague Metro station on Line C serving the Ládví district in the northern part of the city.
-
C.
Kobylisy station
Kobylisy station is a Prague Metro underground station serving the residential district of Kobylisy in the northern part of the city.
-
D.
Chelas station
Chelas station is a Lisbon Metro underground station serving the Chelas neighborhood on the system’s Red Line.
-
E.
Pankrác station
Pankrác station is a Prague Metro stop on Line C serving the Pankrác district in the southern part of the city.
- 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: Roztyly station Triple: [Line C (Prague Metro), connectsStation, Roztyly station]
Generated description
Roztyly station is a Prague Metro station on Line C located in the southern part of the city, serving the Roztyly district and nearby residential and commercial areas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Roztyly station Target entity description: Roztyly station is a Prague Metro station on Line C located in the southern part of the city, serving the Roztyly district and nearby residential and commercial areas.
-
A.
Letňany station
Letňany station is a Prague Metro station in the Letňany district that serves as the northern terminus of Line C.
-
B.
Ládví station
Ládví station is a Prague Metro station on Line C serving the Ládví district in the northern part of the city.
-
C.
Kobylisy station
Kobylisy station is a Prague Metro underground station serving the residential district of Kobylisy in the northern part of the city.
-
D.
Chelas station
Chelas station is a Lisbon Metro underground station serving the Chelas neighborhood on the system’s Red Line.
-
E.
Pankrác station
Pankrác station is a Prague Metro stop on Line C serving the Pankrác district in the southern part of the city.
- 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_6a00077efdf48190ac26f433f6b17dbe |
completed | May 10, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_6a00084d8e308190bd90811392586753 |
completed | May 10, 2026, 4:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0008c7430c81908b9620369c609ad8 |
completed | May 10, 2026, 4:25 a.m. |
Created at: April 10, 2026, 4:59 a.m.