Triple

T19746106
Position Surface form Disambiguated ID Type / Status
Subject TrawsCymru E474254 entity
Predicate hasService P182 FINISHED
Object T2
T2 is a TrawsCymru long-distance bus route in Wales providing inter-town public transport services.
E1393206 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: T2 | Statement: [TrawsCymru, hasService, T2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: T2
Context triple: [TrawsCymru, hasService, T2]
  • A. T2
    T2 is San Francisco International Airport’s Terminal 2, a modern passenger terminal serving domestic flights with updated amenities and design.
  • B. T2
    T2 is a passenger terminal at Berlin Brandenburg Airport that handles check-in, security, and boarding operations for departing and arriving travelers.
  • C. T2
    T2 is one of the tram lines of the Trambaix light rail network serving the Barcelona metropolitan area.
  • D. T2
    T2 is the second passenger terminal at Chicago O'Hare International Airport, serving various domestic and regional airline operations.
  • E. T2
    T2 is a shorthand title for the 1991 science fiction action film "Terminator 2: Judgment Day," directed by James Cameron and starring Arnold Schwarzenegger.
  • 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: T2
Triple: [TrawsCymru, hasService, T2]
Generated description
T2 is a TrawsCymru long-distance bus route in Wales providing inter-town public transport services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: T2
Target entity description: T2 is a TrawsCymru long-distance bus route in Wales providing inter-town public transport services.
  • A. T2
    T2 is a tram line in the Lyon public transport network that connects key districts and suburbs of the city.
  • B. T2
    T2 is one of the tram lines of the Trambaix light rail network serving the Barcelona metropolitan area.
  • C. T2
    T2 is one of the main lines of the Dijon tramway system in Dijon, France, providing urban light-rail transit service across the city.
  • D. T2
    T2 is a Sydney Trains suburban rail service designation used for the Inner West & Leppington Line in the Sydney metropolitan network.
  • E. T2
    T2 is a passenger terminal at Berlin Brandenburg Airport that handles check-in, security, and boarding operations for departing and arriving travelers.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529387ac819094e4d66d630e8b98 completed April 20, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07b501e7348190bf2b14c98cd7cdb0 completed May 16, 2026, 12:06 a.m.
NEDg Description generation batch_6a07b60822688190b840b21173c45054 completed May 16, 2026, 12:10 a.m.
NED2 Entity disambiguation (via description) batch_6a07b6c9fc8c8190825953f50935833e completed May 16, 2026, 12:14 a.m.
Created at: April 10, 2026, 1:47 p.m.