Triple

T5834943
Position Surface form Disambiguated ID Type / Status
Subject London Midland E129443 entity
Predicate fleetIncluded P10916 FINISHED
Object Class 321
Class 321 is a type of British electric multiple unit train widely used for suburban and commuter rail services in the UK.
 E553404 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: Class 321 | Statement: [London Midland, fleetIncluded, Class 321]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Class 321
Context triple: [London Midland, fleetIncluded, Class 321]
  • A. Class 323
    Class 323 is a type of British electric multiple unit train widely used for suburban and commuter rail services in the UK.
  • B. Class 319
    Class 319 is a type of British dual-voltage electric multiple unit train used primarily for commuter and regional services.
  • C. Third Class, Second Grade
    Third Class, Second Grade is a specific rank within the historical Chinese Order of the Double Dragon, denoting a particular level of honor and distinction among its graded classes.
  • D. Classe
    Classe is a historic coastal area near Ravenna in Italy, renowned for its early Christian monuments and archaeological remains.
  • E. Y class
    Y class is the standard economy fare class used by airlines, typically representing full-fare economy tickets with the least restrictions on changes and refunds.
  • 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: Class 321
Triple: [London Midland, fleetIncluded, Class 321]
Generated description
Class 321 is a type of British electric multiple unit train widely used for suburban and commuter rail services in the UK.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Class 321
Target entity description: Class 321 is a type of British electric multiple unit train widely used for suburban and commuter rail services in the UK.
  • A. Class 323
    Class 323 is a type of British electric multiple unit train widely used for suburban and commuter rail services in the UK.
  • B. Class 319
    Class 319 is a type of British dual-voltage electric multiple unit train used primarily for commuter and regional services.
  • C. Third Class, Second Grade
    Third Class, Second Grade is a specific rank within the historical Chinese Order of the Double Dragon, denoting a particular level of honor and distinction among its graded classes.
  • D. Classe
    Classe is a historic coastal area near Ravenna in Italy, renowned for its early Christian monuments and archaeological remains.
  • E. Y class
    Y class is the standard economy fare class used by airlines, typically representing full-fare economy tickets with the least restrictions on changes and refunds.
  • 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_69c0084af79c81908af128ccc29983d0 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c034a1e6a88190b1aac05511793315 completed March 22, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b0ef1c988190b452158b560cf39f completed March 23, 2026, 3:18 a.m.
NEDg Description generation batch_69c0b1e5cdc081908d0d2b76701d20ea completed March 23, 2026, 3:22 a.m.
NED2 Entity disambiguation (via description) batch_69c0b24d7d148190901e233d815d21ad completed March 23, 2026, 3:23 a.m.
Created at: March 22, 2026, 3:54 p.m.