Triple

T8741282
Position Surface form Disambiguated ID Type / Status
Subject Brest Airport E207506 entity
Predicate icaoCode P419 FINISHED
Object UMBB
UMBB is the ICAO airport code for Brest Airport in Belarus, used in aviation for flight planning and air traffic control.
 E754435 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: UMBB | Statement: [Brest Airport, icaoCode, UMBB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UMBB
Context triple: [Brest Airport, icaoCode, UMBB]
  • A. UMM
    UMM is a small public liberal arts college campus of the University of Minnesota system located in Morris, Minnesota.
  • B. UMM
    UMM is a private Islamic university in Malang, Indonesia, affiliated with the Muhammadiyah organization and known for its wide range of academic programs.
  • C. UMB
    UMB is a public research university located on the waterfront in Boston, Massachusetts, known for its diverse student body and strong programs in liberal arts, sciences, and professional studies.
  • D. UMB
    UMB is the Indian Railways station code for Ambala Cantonment, a major railway junction in Haryana, India.
  • E. UM
    UM is the commonly used abbreviation for the University of Miami, a private research university located in Coral Gables, Florida.
  • 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: UMBB
Triple: [Brest Airport, icaoCode, UMBB]
Generated description
UMBB is the ICAO airport code for Brest Airport in Belarus, used in aviation for flight planning and air traffic control.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UMBB
Target entity description: UMBB is the ICAO airport code for Brest Airport in Belarus, used in aviation for flight planning and air traffic control.
  • A. UMM
    UMM is a small public liberal arts college campus of the University of Minnesota system located in Morris, Minnesota.
  • B. UMM
    UMM is a private Islamic university in Malang, Indonesia, affiliated with the Muhammadiyah organization and known for its wide range of academic programs.
  • C. UMB
    UMB is the Indian Railways station code for Ambala Cantonment, a major railway junction in Haryana, India.
  • D. UMB
    UMB is a public research university located on the waterfront in Boston, Massachusetts, known for its diverse student body and strong programs in liberal arts, sciences, and professional studies.
  • E. UM
    UM is the commonly used abbreviation for Maastricht University, a public research university located in Maastricht, the Netherlands.
  • 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_69ca835a03a081909d4d4cd01a18c9fb completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d4a0cf481909c770cb39fd00fcd completed March 31, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf42f282e48190ad158063e265e0f0 completed April 3, 2026, 4:32 a.m.
NEDg Description generation batch_69cf4433605c8190991f95d19726cab8 completed April 3, 2026, 4:38 a.m.
NED2 Entity disambiguation (via description) batch_69cf44c20b408190b622d18f78277802 completed April 3, 2026, 4:40 a.m.
Created at: March 30, 2026, 6:38 p.m.