Triple

T11552769
Position Surface form Disambiguated ID Type / Status
Subject Bournville railway station E273936 entity
Predicate hasStationCode P1289 FINISHED
Object BRV
BRV is the National Rail station code for Bournville railway station in Birmingham, England.
E932750 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: BRV | Statement: [Bournville railway station, hasStationCode, BRV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BRV
Context triple: [Bournville railway station, hasStationCode, BRV]
  • A. BR2
    BR2 is a UK postcode district covering parts of Hayes and surrounding areas in the London Borough of Bromley in southeast England.
  • B. BR-040
    BR-040 is a major Brazilian federal highway that connects key cities including Rio de Janeiro, Juiz de Fora, Belo Horizonte, and Brasília.
  • C. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • D. BRW
    BRW is the IATA airport code for Wiley Post–Will Rogers Memorial Airport in Utqiaġvik, Alaska, a key air transport hub for the Arctic region.
  • E. BRG
    BRG is the stock ticker symbol for Borregaard, a Norwegian company specializing in advanced and sustainable biochemicals derived from wood.
  • 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: BRV
Triple: [Bournville railway station, hasStationCode, BRV]
Generated description
BRV is the National Rail station code for Bournville railway station in Birmingham, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BRV
Target entity description: BRV is the National Rail station code for Bournville railway station in Birmingham, England.
  • A. BR2
    BR2 is a UK postcode district covering parts of Hayes and surrounding areas in the London Borough of Bromley in southeast England.
  • B. BR-040
    BR-040 is a major Brazilian federal highway that connects key cities including Rio de Janeiro, Juiz de Fora, Belo Horizonte, and Brasília.
  • C. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • D. BRW
    BRW is the IATA airport code for Wiley Post–Will Rogers Memorial Airport in Utqiaġvik, Alaska, a key air transport hub for the Arctic region.
  • E. BRG
    BRG is the stock ticker symbol for Borregaard, a Norwegian company specializing in advanced and sustainable biochemicals derived from wood.
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88a85b9ac8190a57c1fdaeacbe3d6 completed April 10, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e851a6688190996580a077496833 completed April 21, 2026, 3 a.m.
NEDg Description generation batch_69e6ef93e7d88190af3853b82de23c1b completed April 21, 2026, 3:31 a.m.
NED2 Entity disambiguation (via description) batch_69e6f9144afc819081ee7f78e32ad39a completed April 21, 2026, 4:12 a.m.
Created at: April 8, 2026, 9:37 p.m.