Triple

T23305138
Position Surface form Disambiguated ID Type / Status
Subject Prague 9 E590414 entity
Predicate hasMetroLine P17559 FINISHED
Object Line C
Line C is one of the main lines of the Prague Metro, running in a north–south direction and serving key districts including the Prague 9 area.
 E390323 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: Line C | Statement: [Prague 9, hasMetroLine, Line C]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Line C
Context triple: [Prague 9, hasMetroLine, Line C]
  • A. Line C
    Line C is one of the routes of the Porto Metro light rail network in Porto, Portugal, serving suburban and urban areas along its corridor.
  • B. Line C
    Line C is one of the routes of the Strasbourg tramway network, providing urban light-rail transit service within the city and its suburbs.
  • C. Line C
    Line C is one of the main routes of the Rotterdam Metro rapid transit system in the Netherlands, connecting key districts across the metropolitan area.
  • D. Line C
    Line C is one of the lines of the Lyon Metro system in France, known for its steep rack railway section connecting the city center to the Croix-Rousse hill.
  • E. Line C
    Line C is one of the main lines of the Buenos Aires Underground, running north–south through central Buenos Aires and connecting key transport hubs in 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: Line C
Triple: [Prague 9, hasMetroLine, Line C]
Generated description
Line C is one of the main lines of the Prague Metro, running in a north–south direction and serving key districts including the Prague 9 area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Line C
Target entity description: Line C is one of the main lines of the Prague Metro, running in a north–south direction and serving key districts including the Prague 9 area.
  • A. Line C chosen
    Line C is one of the main lines of the Prague Metro, running in a north–south direction and serving as a key backbone of the city’s rapid transit network.
  • B. Line C
    Line C is one of the main routes of the Rotterdam Metro rapid transit system in the Netherlands, connecting key districts across the metropolitan area.
  • C. Line C
    Line C is one of the main lines of the Buenos Aires Underground, running north–south through central Buenos Aires and connecting key transport hubs in the city.
  • D. Line C
    Line C is one of the lines of the Lyon Metro system in France, known for its steep rack railway section connecting the city center to the Croix-Rousse hill.
  • E. Line C
    Line C is one of the routes of the Porto Metro light rail network in Porto, Portugal, serving suburban and urban areas along its corridor.
  • F. None of above.

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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19725b248819089e61efb82e3440f completed April 29, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c4c9934ec819094ebbe6e61d18ab7 completed May 19, 2026, 11:42 a.m.
NEDg Description generation batch_6a0c4f37e390819083df9a959acf3a32 completed May 19, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0c4fdafde88190a7ac791189acde68 completed May 19, 2026, 11:56 a.m.
Created at: April 17, 2026, 5:04 p.m.