Triple

T5794638
Position Surface form Disambiguated ID Type / Status
Subject Bram Fischer International Airport E128477 entity
Predicate IATAcode P418 FINISHED
Object BFN
BFN is the IATA airport code for Bram Fischer International Airport, the main airport serving Bloemfontein in South Africa.
E364108 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: BFN | Statement: [Bram Fischer International Airport, IATAcode, BFN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BFN
Context triple: [Bram Fischer International Airport, IATAcode, BFN]
  • A. BFN
    BFN is the National Rail station code for Byfleet & New Haw railway station in Surrey, England.
  • B. BF
    BF is the IATA airline designator for French Bee, a French low-cost long-haul carrier.
  • C. BF
    BF is the two-letter ISO 3166-1 alpha-2 country code assigned to Burkina Faso.
  • D. Bf
    Bf is the aircraft designation prefix historically used for military aircraft designed or built by the German manufacturer Bayerische Flugzeugwerke, notably including early Messerschmitt fighters.
  • E. EBFN
    EBFN is the ICAO airport code for Koksijde Air Base, a military airfield in Belgium.
  • 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: BFN
Triple: [Bram Fischer International Airport, IATAcode, BFN]
Generated description
BFN is the IATA airport code for Bram Fischer International Airport, the main airport serving Bloemfontein in South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BFN
Target entity description: BFN is the IATA airport code for Bram Fischer International Airport, the main airport serving Bloemfontein in South Africa.
  • A. BFN chosen
    BFN is the National Rail station code for Byfleet & New Haw railway station in Surrey, England.
  • B. BF
    BF is the IATA airline designator for French Bee, a French low-cost long-haul carrier.
  • C. BF
    BF is the two-letter ISO 3166-1 alpha-2 country code assigned to Burkina Faso.
  • D. Bf
    Bf is the aircraft designation prefix historically used for military aircraft designed or built by the German manufacturer Bayerische Flugzeugwerke, notably including early Messerschmitt fighters.
  • E. EBFN
    EBFN is the ICAO airport code for Koksijde Air Base, a military airfield in Belgium.
  • F. None of above.

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_69c00845ca68819081a2ce3ecca577f7 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02a91c7788190936671bf816d3772 completed March 22, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c098286c1c8190b77cbaeda327dba4 completed March 23, 2026, 1:32 a.m.
NEDg Description generation batch_69c098a0325c81909a1326b94e40ed50 completed March 23, 2026, 1:34 a.m.
NED2 Entity disambiguation (via description) batch_69c09943deec819085992c4e44050a34 completed March 23, 2026, 1:37 a.m.
Created at: March 22, 2026, 3:51 p.m.