Triple

T10857123
Position Surface form Disambiguated ID Type / Status
Subject British Rail Class 37 E256295 entity
Predicate operator P179 FINISHED
Object EWS
EWS (English, Welsh & Scottish Railway) was a major British rail freight company that operated a large fleet of locomotives and became the dominant freight operator in the UK before being rebranded as DB Cargo UK.
 E889003 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: EWS | Statement: [British Rail Class 37, operator, EWS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EWS
Context triple: [British Rail Class 37, operator, EWS]
  • A. ESW
    ESW is the vehicle registration code for the German town and district of Eschwege in the state of Hesse.
  • B. EWE
    EWE is the National Rail station code for Ewell West railway station in Surrey, England.
  • C. WES
    WES is a commuter rail service in the Portland, Oregon metropolitan area that connects Beaverton and Wilsonville.
  • D. WES
    WES is the standard abbreviation for the Westchester Knicks, the NBA G League affiliate of the New York Knicks.
  • E. WES
    WES is the vehicle registration code used on license plates for vehicles registered in the Wesel district of Germany.
  • 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: EWS
Triple: [British Rail Class 37, operator, EWS]
Generated description
EWS (English, Welsh & Scottish Railway) was a major British rail freight company that operated a large fleet of locomotives and became the dominant freight operator in the UK before being rebranded as DB Cargo UK.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EWS
Target entity description: EWS (English, Welsh & Scottish Railway) was a major British rail freight company that operated a large fleet of locomotives and became the dominant freight operator in the UK before being rebranded as DB Cargo UK.
  • A. ESW
    ESW is the vehicle registration code for the German town and district of Eschwege in the state of Hesse.
  • B. EWE
    EWE is the National Rail station code for Ewell West railway station in Surrey, England.
  • C. WES
    WES is a commuter rail service in the Portland, Oregon metropolitan area that connects Beaverton and Wilsonville.
  • D. WES
    WES is the vehicle registration code used on license plates for vehicles registered in the Wesel district of Germany.
  • E. WES
    WES is the standard abbreviation for the Westchester Knicks, the NBA G League affiliate of the New York Knicks.
  • 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7513695ac8190b5812e977a422c37 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb197808c8190b1c80aeb2144a909 completed April 14, 2026, 9:28 p.m.
NEDg Description generation batch_69dec25660dc8190a4444a1099e7e40c completed April 14, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69dec7cdcd988190bb6508838bea48de completed April 14, 2026, 11:03 p.m.
Created at: April 8, 2026, 9:20 p.m.