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.