Triple

T19524147
Position Surface form Disambiguated ID Type / Status
Subject Riga tram lines E488476 entity
Predicate hasDepot P2413 FINISHED
Object Brasa tram depot
Brasa tram depot is a major tram maintenance and storage facility in Riga, Latvia, serving the city’s tram network.
 E1380372 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: Brasa tram depot | Statement: [Riga tram lines, hasDepot, Brasa tram depot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Brasa tram depot
Context triple: [Riga tram lines, hasDepot, Brasa tram depot]
  • A. Pontinha depot
    Pontinha depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
  • B. Eybens tram depot
    Eybens tram depot is a maintenance and storage facility serving the Grenoble tramway network in the suburb of Eybens, France.
  • C. Nangang Depot
    Nangang Depot is a major maintenance and storage facility serving Taipei's metro system in the Nangang District.
  • D. Motol tram depot
    Motol tram depot is a major tram facility in Prague used for housing, maintaining, and dispatching vehicles on the city’s tram network.
  • E. Munyang Depot
    Munyang Depot is a maintenance and storage facility serving the Daegu Metro system in Daegu, South Korea.
  • 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: Brasa tram depot
Triple: [Riga tram lines, hasDepot, Brasa tram depot]
Generated description
Brasa tram depot is a major tram maintenance and storage facility in Riga, Latvia, serving the city’s tram network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Brasa tram depot
Target entity description: Brasa tram depot is a major tram maintenance and storage facility in Riga, Latvia, serving the city’s tram network.
  • A. Pontinha depot
    Pontinha depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
  • B. Eybens tram depot
    Eybens tram depot is a maintenance and storage facility serving the Grenoble tramway network in the suburb of Eybens, France.
  • C. Nangang Depot
    Nangang Depot is a major maintenance and storage facility serving Taipei's metro system in the Nangang District.
  • D. Motol tram depot
    Motol tram depot is a major tram facility in Prague used for housing, maintaining, and dispatching vehicles on the city’s tram network.
  • E. Munyang Depot
    Munyang Depot is a maintenance and storage facility serving the Daegu Metro system in Daegu, South Korea.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e636392444819094f6a2aa1cdf3d42 completed April 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07472cadd88190a7306b8891141157 completed May 15, 2026, 4:17 p.m.
NEDg Description generation batch_6a07484fcb28819082922c817170d118 completed May 15, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_6a07492259488190a8c405598f9c8878 completed May 15, 2026, 4:26 p.m.
Created at: April 10, 2026, 1:41 p.m.