Triple

T14404687
Position Surface form Disambiguated ID Type / Status
Subject Cogan railway station E357165 entity
Predicate stationCode P1289 FINISHED
Object CGN
CGN is the National Rail station code for Cogan railway station in the Vale of Glamorgan, Wales.
E1097538 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: CGN | Statement: [Cogan railway station, stationCode, CGN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CGN
Context triple: [Cogan railway station, stationCode, CGN]
  • A. CGN
    CGN is the IATA airport code for Cologne Bonn Airport, a major international airport serving the Cologne and Bonn region in western Germany.
  • B. CGN
    CGN is a Swiss company that operates passenger ferry and cruise services on Lake Geneva.
  • C. CN-GS
    CN-GS is the ISO 3166-2 code representing Gansu Province, a landlocked region in north-central China known for its role along the historic Silk Road.
  • D. KGN
    KGN is the standard three-letter abbreviation used for the Kingston Frontenacs, a major junior ice hockey team in the Ontario Hockey League.
  • E. CnaG
    CnaG is the Irish-language abbreviation for Cumann na nGaedheal, the pro-Treaty political party that governed the Irish Free State in the 1920s.
  • 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: CGN
Triple: [Cogan railway station, stationCode, CGN]
Generated description
CGN is the National Rail station code for Cogan railway station in the Vale of Glamorgan, Wales.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CGN
Target entity description: CGN is the National Rail station code for Cogan railway station in the Vale of Glamorgan, Wales.
  • A. CGN
    CGN is a Swiss company that operates passenger ferry and cruise services on Lake Geneva.
  • B. CGN
    CGN is the IATA airport code for Cologne Bonn Airport, a major international airport serving the Cologne and Bonn region in western Germany.
  • C. CN-GS
    CN-GS is the ISO 3166-2 code representing Gansu Province, a landlocked region in north-central China known for its role along the historic Silk Road.
  • D. KGN
    KGN is the standard three-letter abbreviation used for the Kingston Frontenacs, a major junior ice hockey team in the Ontario Hockey League.
  • E. CnaG
    CnaG is the Irish-language abbreviation for Cumann na nGaedheal, the pro-Treaty political party that governed the Irish Free State in the 1920s.
  • 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90860ae481908e175decda8624d5 completed April 14, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5523267081908d972b60b6039528 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd5671e4688190ab1b7a7ed6c0cfb8 completed May 8, 2026, 3:20 a.m.
NED2 Entity disambiguation (via description) batch_69fd57710f648190a1344ac1363acce1 completed May 8, 2026, 3:24 a.m.
Created at: April 10, 2026, 1:17 a.m.