Triple

T18597336
Position Surface form Disambiguated ID Type / Status
Subject Aarhus Letbane E454525 entity
Predicate hasLine P35 FINISHED
Object Line L3
Line L3 is a light rail route that forms part of the Aarhus Letbane tram network in Aarhus, Denmark.
E1334786 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 L3 | Statement: [Aarhus Letbane, hasLine, Line L3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Line L3
Context triple: [Aarhus Letbane, hasLine, Line L3]
  • A. Line L2
    Line L2 is one of the light rail routes of the Aarhus Letbane system in Aarhus, Denmark, providing urban and regional passenger transport.
  • B. Line 3
    Line 3 is a major line of the Moscow Metro system, known for serving central Moscow and connecting key residential and commercial districts.
  • C. Line 3
    Line 3 is a Culver CityBus route in the Los Angeles area that connects key destinations across Culver City and nearby communities.
  • D. Line 3
    Line 3 is a metro line that intersects with Metro Line 9 within the same urban rail network, serving as one of its connecting routes.
  • E. Line 3
    Line 3 is a rapid transit line of the Hangzhou Metro system in Hangzhou, China, serving as part of the city's expanding urban 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: Line L3
Triple: [Aarhus Letbane, hasLine, Line L3]
Generated description
Line L3 is a light rail route that forms part of the Aarhus Letbane tram network in Aarhus, Denmark.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Line L3
Target entity description: Line L3 is a light rail route that forms part of the Aarhus Letbane tram network in Aarhus, Denmark.
  • A. Line L2
    Line L2 is one of the light rail routes of the Aarhus Letbane system in Aarhus, Denmark, providing urban and regional passenger transport.
  • B. Line 3
    Line 3 is a major line of the Moscow Metro system, known for serving central Moscow and connecting key residential and commercial districts.
  • C. Line 3
    Line 3 is a Culver CityBus route in the Los Angeles area that connects key destinations across Culver City and nearby communities.
  • D. Line 3
    Line 3 is a metro line that intersects with Metro Line 9 within the same urban rail network, serving as one of its connecting routes.
  • E. Line 3
    Line 3 is a rapid transit line of the Hangzhou Metro system in Hangzhou, China, serving as part of the city's expanding urban 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5474ce0c08190b440cbe86b6ef7b9 completed April 19, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d6eb92c8190aa0c1f4eb0deb5cb completed May 13, 2026, 11:46 p.m.
NEDg Description generation batch_6a050e04ebd881909120edb46168fbcb completed May 13, 2026, 11:49 p.m.
NED2 Entity disambiguation (via description) batch_6a050e6112e88190a399cf58ea6c8401 completed May 13, 2026, 11:50 p.m.
Created at: April 10, 2026, 11:44 a.m.