Triple

T14833708
Position Surface form Disambiguated ID Type / Status
Subject Ouagadougou Airport E348773 entity
Predicate hasRunway P105 FINISHED
Object Runway 04/22
Runway 04/22 is a principal paved runway used for aircraft takeoffs and landings at Ouagadougou Airport in Burkina Faso.
 E1134474 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: Runway 04/22 | Statement: [Ouagadougou Airport, hasRunway, Runway 04/22]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 04/22
Context triple: [Ouagadougou Airport, hasRunway, Runway 04/22]
  • A. Runway 04/22
    Runway 04/22 is one of the primary paved runways used for aircraft takeoffs and landings at El Paso International Airport in Texas.
  • B. Runway 04/22
    Runway 04/22 is a primary paved runway at Palmdale Regional Airport in California, used for general aviation and regional air traffic operations.
  • C. Runway 04/22
    Runway 04/22 is one of the primary paved runways at William P. Hobby Airport in Houston, Texas, used for commercial and general aviation operations.
  • D. Runway 04/22
    Runway 04/22 is one of the primary paved runways at San Antonio International Airport, used for handling a mix of commercial and general aviation traffic.
  • E. Runway 04/22
    Runway 04/22 is a primary paved runway at Leoš Janáček Airport Ostrava in the Czech Republic, used for handling both domestic and international air traffic.
  • 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: Runway 04/22
Triple: [Ouagadougou Airport, hasRunway, Runway 04/22]
Generated description
Runway 04/22 is a principal paved runway used for aircraft takeoffs and landings at Ouagadougou Airport in Burkina Faso.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 04/22
Target entity description: Runway 04/22 is a principal paved runway used for aircraft takeoffs and landings at Ouagadougou Airport in Burkina Faso.
  • A. Runway 04/22
    Runway 04/22 is a primary paved runway at Leoš Janáček Airport Ostrava in the Czech Republic, used for handling both domestic and international air traffic.
  • B. Runway 04/22
    Runway 04/22 is one of LaGuardia Airport’s primary runways, used for handling a significant portion of the airport’s takeoff and landing traffic.
  • C. Runway 04/22
    Runway 04/22 is one of the primary paved runways used for aircraft takeoffs and landings at El Paso International Airport in Texas.
  • D. Runway 04/22
    Runway 04/22 is a primary paved runway at Palmdale Regional Airport in California, used for general aviation and regional air traffic operations.
  • E. Runway 04/22
    Runway 04/22 is one of the primary paved runways at William P. Hobby Airport in Houston, Texas, used for commercial and general aviation operations.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded075af0881908fb35a9e7ee46749 completed April 14, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fea5a421e88190a7cd359209ae2818 completed May 9, 2026, 3:10 a.m.
NEDg Description generation batch_69fea694090c8190a449725dcdd3a37b completed May 9, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_69fea76e2ff8819099acea30c49bd5ed completed May 9, 2026, 3:18 a.m.
Created at: April 10, 2026, 1:52 a.m.