Triple

T21219423
Position Surface form Disambiguated ID Type / Status
Subject Bedford railway station E522924 entity
Predicate stationCode P1289 FINISHED
Object BDM
BDM is the National Rail station code for Bedford railway station in Bedfordshire, England.
 E1471336 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: BDM | Statement: [Bedford railway station, stationCode, BDM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BDM
Context triple: [Bedford railway station, stationCode, BDM]
  • A. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • B. BdU
    BdU was the German World War II command authority responsible for directing and overseeing the operations of the Kriegsmarine’s U-boat fleet.
  • C. BDP
    BDP is a major international architecture and engineering firm known for designing prominent public and cultural buildings in the UK and worldwide.
  • D. BdE
    BdE is the commonly used abbreviation for the Bank of Spain, the country’s central bank responsible for monetary policy and financial supervision.
  • E. Bdl
    Bdl is the station code for Bloemendaal railway station in the Netherlands.
  • 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: BDM
Triple: [Bedford railway station, stationCode, BDM]
Generated description
BDM is the National Rail station code for Bedford railway station in Bedfordshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BDM
Target entity description: BDM is the National Rail station code for Bedford railway station in Bedfordshire, England.
  • A. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • B. BdU
    BdU was the German World War II command authority responsible for directing and overseeing the operations of the Kriegsmarine’s U-boat fleet.
  • C. BDP
    BDP is a major international architecture and engineering firm known for designing prominent public and cultural buildings in the UK and worldwide.
  • D. BdE
    BdE is the commonly used abbreviation for the Bank of Spain, the country’s central bank responsible for monetary policy and financial supervision.
  • E. Bdl
    Bdl is the station code for Bloemendaal railway station in the Netherlands.
  • 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_69e0b511ed84819099b449b4a111085c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73476d93481909c6c99dcc0b16123 completed April 21, 2026, 8:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a097edb6de4819094cf7a50670afdfa completed May 17, 2026, 8:39 a.m.
NEDg Description generation batch_6a097f5016348190aeb01856a5c57b41 completed May 17, 2026, 8:41 a.m.
NED2 Entity disambiguation (via description) batch_6a097fe399048190a1b29f16d8e46d8d completed May 17, 2026, 8:44 a.m.
Created at: April 16, 2026, 3:43 p.m.