Triple

T17882009
Position Surface form Disambiguated ID Type / Status
Subject Prince Albert (Glass Field) Airport E447109 entity
Predicate hasIATACode P2569 FINISHED
Object YPA
YPA is the IATA airport code for Prince Albert (Glass Field) Airport in Saskatchewan, Canada.
E1294195 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: YPA | Statement: [Prince Albert (Glass Field) Airport, hasIATACode, YPA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YPA
Context triple: [Prince Albert (Glass Field) Airport, hasIATACode, YPA]
  • A. YDPA
    YDPA is the common abbreviation for the Yang di-Pertuan Agong, the constitutional monarch and head of state of Malaysia.
  • B. YVP
    YVP is the National Rail station code for Yeovil Pen Mill railway station in Somerset, England.
  • C. YVP
    YVP is the IATA airport code for Kuujjuaq Airport, a regional airport serving the community of Kuujjuaq in northern Quebec, Canada.
  • D. YIA
    YIA is the IATA airport code for Yogyakarta International Airport, the main commercial air gateway serving the Yogyakarta region in Indonesia.
  • E. IAYP
    IAYP is a youth development program, based on the Duke of Edinburgh’s Award framework, that encourages young people to build skills, engage in physical activity, and participate in community service.
  • 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: YPA
Triple: [Prince Albert (Glass Field) Airport, hasIATACode, YPA]
Generated description
YPA is the IATA airport code for Prince Albert (Glass Field) Airport in Saskatchewan, Canada.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: YPA
Target entity description: YPA is the IATA airport code for Prince Albert (Glass Field) Airport in Saskatchewan, Canada.
  • A. YDPA
    YDPA is the common abbreviation for the Yang di-Pertuan Agong, the constitutional monarch and head of state of Malaysia.
  • B. YVP
    YVP is the National Rail station code for Yeovil Pen Mill railway station in Somerset, England.
  • C. YVP
    YVP is the IATA airport code for Kuujjuaq Airport, a regional airport serving the community of Kuujjuaq in northern Quebec, Canada.
  • D. YIA
    YIA is the IATA airport code for Yogyakarta International Airport, the main commercial air gateway serving the Yogyakarta region in Indonesia.
  • E. IAYP
    IAYP is a youth development program, based on the Duke of Edinburgh’s Award framework, that encourages young people to build skills, engage in physical activity, and participate in community service.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c0f40fc8190b2e615b41829f5df completed April 19, 2026, 9:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0313d5d12c81909b56381cddbe355a completed May 12, 2026, 11:49 a.m.
NEDg Description generation batch_6a0314a4fa748190a63ecda792b7669a completed May 12, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0315a8d6e88190b6d532f22dd8088c completed May 12, 2026, 11:57 a.m.
Created at: April 10, 2026, 10:18 a.m.