Triple

T23493050
Position Surface form Disambiguated ID Type / Status
Subject Innsbruck tram system E571627 entity
Predicate hasLine P35 FINISHED
Object Line 6
Line 6 is a scenic tram route in Innsbruck, Austria, known for its picturesque journey through mountainous and forested areas on the city’s tram network.
E1588510 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 6 | Statement: [Innsbruck tram system, hasLine, Line 6]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Line 6
Context triple: [Innsbruck tram system, hasLine, Line 6]
  • A. Line 6
    Line 6 is a major rapid transit route in the Beijing Subway system that runs east–west across the city, helping to relieve congestion on other central lines.
  • B. Line 6
    Line 6 is a major north–south route of the Tehran Metro system, serving numerous key districts across Iran’s capital city.
  • C. Line 6
    Line 6 is a planned rapid transit route within the future Ho Chi Minh City Metro system in Vietnam.
  • D. Line 6
    Line 6 is a route of the Tunis Metro light rail network serving passengers within the Tunis metropolitan area.
  • E. Line 6
    Line 6 is one of the lines of the Paris Métro, known for its largely elevated route offering views of the city, including the Eiffel Tower.
  • 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 6
Triple: [Innsbruck tram system, hasLine, Line 6]
Generated description
Line 6 is a scenic tram route in Innsbruck, Austria, known for its picturesque journey through mountainous and forested areas on the city’s tram network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Line 6
Target entity description: Line 6 is a scenic tram route in Innsbruck, Austria, known for its picturesque journey through mountainous and forested areas on the city’s tram network.
  • A. Line 6
    Line 6 is a rapid transit route of the Brussels Metro system that serves key stations in Belgium’s capital.
  • B. Line 6
    Line 6 is a modern, fully automated metro line in the Santiago Metro system in Chile, known for its driverless trains and advanced safety features.
  • C. Line 6
    Line 6 is one of the lines of the Paris Métro, known for its largely elevated route offering views of the city, including the Eiffel Tower.
  • D. Line 6
    Line 6 is a rapid transit line of the Shanghai Metro system serving several districts along the city’s eastern side.
  • E. Line 6
    Line 6 is a major route of the Seoul Metropolitan Subway system that runs in a semi-circular path through northern Seoul, connecting numerous residential and commercial districts.
  • 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_69e245b4829881909b77a70e942bbd54 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7dd56408190b459077e433ed1c3 completed April 29, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c826ff3848190a3cdf82c26b6e22e completed May 19, 2026, 3:32 p.m.
NEDg Description generation batch_6a0ca6f229308190bf72b52fd44144d3 completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca7e9e9988190ac3bedb9ecb8ce06 completed May 19, 2026, 6:11 p.m.
Created at: April 17, 2026, 6:05 p.m.