Triple

T22278718
Position Surface form Disambiguated ID Type / Status
Subject Garoua International Airport E550675 entity
Predicate ICAO code P419 FINISHED
Object FKKR
FKKR is the ICAO airport code for Garoua International Airport in Garoua, Cameroon.
 E1529032 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: FKKR | Statement: [Garoua International Airport, ICAO code, FKKR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FKKR
Context triple: [Garoua International Airport, ICAO code, FKKR]
  • A. FKKD
    FKKD is the ICAO airport code for Douala International Airport, the main international gateway to Douala, Cameroon.
  • B. FKK
    FKK is the National Rail station code assigned to Falkirk High railway station in Scotland.
  • C. FKRM
    FKRM is the Faculty of Kinesiology and Recreation Management, an academic unit focused on the study of human movement, sport, health, and recreation.
  • D. FKW
    FKW is the National Rail station code for Folkestone West railway station in Kent, England.
  • E. FK
    FK is the common abbreviation for the Swedish Social Insurance Agency, the government body responsible for administering social security benefits in Sweden.
  • 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: FKKR
Triple: [Garoua International Airport, ICAO code, FKKR]
Generated description
FKKR is the ICAO airport code for Garoua International Airport in Garoua, Cameroon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FKKR
Target entity description: FKKR is the ICAO airport code for Garoua International Airport in Garoua, Cameroon.
  • A. FKKD
    FKKD is the ICAO airport code for Douala International Airport, the main international gateway to Douala, Cameroon.
  • B. FKK
    FKK is the National Rail station code assigned to Falkirk High railway station in Scotland.
  • C. FKRM
    FKRM is the Faculty of Kinesiology and Recreation Management, an academic unit focused on the study of human movement, sport, health, and recreation.
  • D. FKW
    FKW is the National Rail station code for Folkestone West railway station in Kent, England.
  • E. FK
    FK is the common abbreviation for the Swedish Social Insurance Agency, the government body responsible for administering social security benefits in Sweden.
  • 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_69e11e44d538819097c6b8f333af3352 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea96948819081c1ae6c7b11ab62 completed April 29, 2026, 12:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0abca612008190bcb1c38523223ed7 completed May 18, 2026, 7:15 a.m.
NEDg Description generation batch_6a0ac0d258d88190a73427e02373a4bc completed May 18, 2026, 7:33 a.m.
NED2 Entity disambiguation (via description) batch_6a0ac1e9666c8190b183c069deaf487c completed May 18, 2026, 7:38 a.m.
Created at: April 16, 2026, 8:40 p.m.