Triple

T6720019
Position Surface form Disambiguated ID Type / Status
Subject British Rail Class 165 E153370 entity
Predicate manufacturer P490 FINISHED
Object BREL York
BREL York was a major British railway engineering works in York that built and maintained rolling stock for the national rail network.
E614013 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: BREL York | Statement: [British Rail Class 165, manufacturer, BREL York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BREL York
Context triple: [British Rail Class 165, manufacturer, BREL York]
  • A. BREL Derby
    BREL Derby was a major British railway engineering works in Derby that built and maintained rolling stock for the UK rail network.
  • B. Fairlight
    Fairlight is a coastal village in East Sussex, England, known for its scenic cliffs, countryside, and proximity to Hastings.
  • C. Blatch
    Blatch is the surname of Nora Stanton Blatch, an early 20th-century American civil engineer, suffragist, and women's rights activist.
  • D. Yorke
    Yorke is an English surname historically associated with prominent figures in law, politics, and public life in Britain.
  • E. De Peel
    De Peel is a peat bog and nature reserve region in the southeastern Netherlands, known for its wetlands, heathlands, and rich biodiversity.
  • 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: BREL York
Triple: [British Rail Class 165, manufacturer, BREL York]
Generated description
BREL York was a major British railway engineering works in York that built and maintained rolling stock for the national rail network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BREL York
Target entity description: BREL York was a major British railway engineering works in York that built and maintained rolling stock for the national rail network.
  • A. BREL Derby
    BREL Derby was a major British railway engineering works in Derby that built and maintained rolling stock for the UK rail network.
  • B. Fairlight
    Fairlight is a coastal village in East Sussex, England, known for its scenic cliffs, countryside, and proximity to Hastings.
  • C. Blatch
    Blatch is the surname of Nora Stanton Blatch, an early 20th-century American civil engineer, suffragist, and women's rights activist.
  • D. Yorke
    Yorke is an English surname historically associated with prominent figures in law, politics, and public life in Britain.
  • E. De Peel
    De Peel is a peat bog and nature reserve region in the southeastern Netherlands, known for its wetlands, heathlands, and rich biodiversity.
  • 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_69c68809b4608190a2509ddb5ab87f05 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d137084881908e04ee6b2bd45585 completed March 27, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7009f1e208190891c4542a6c613ac completed March 27, 2026, 10:11 p.m.
NEDg Description generation batch_69c7048843e081908b70942a91a390fe completed March 27, 2026, 10:28 p.m.
NED2 Entity disambiguation (via description) batch_69c705240f54819094e8715ffd66b352 completed March 27, 2026, 10:31 p.m.
Created at: March 27, 2026, 2:07 p.m.