Triple

T3569735
Position Surface form Disambiguated ID Type / Status
Subject Canberra Airport E75538 entity
Predicate hasRunway P105 FINISHED
Object Runway 12/30
Runway 12/30 is a principal paved runway at Canberra Airport used for handling domestic and international air traffic.
 E452655 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 12/30 | Statement: [Canberra Airport, hasRunway, Runway 12/30]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 12/30
Context triple: [Canberra Airport, hasRunway, Runway 12/30]
  • A. Runway 12/30
    Runway 12/30 is one of the primary paved runways used for aircraft takeoffs and landings at Washington Dulles International Airport in Virginia.
  • B. Runway 12/30
    Runway 12/30 is the primary paved runway used for commercial flight operations at L.F. Wade International Airport in Bermuda.
  • C. Runway 12/30
    Runway 12/30 is a primary paved runway at San Carlos Airport in California, used mainly for general aviation operations.
  • D. Runway 12/30
    Runway 12/30 is one of the primary paved runways at Chennai International Airport in India, used for handling both domestic and international air traffic.
  • E. Runway 12R/30L
    Runway 12R/30L is one of the primary paved runways used for aircraft takeoffs and landings at Nikola Tesla International Airport in Belgrade, Serbia.
  • 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 12/30
Triple: [Canberra Airport, hasRunway, Runway 12/30]
Generated description
Runway 12/30 is a principal paved runway at Canberra Airport used for handling domestic and international air traffic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 12/30
Target entity description: Runway 12/30 is a principal paved runway at Canberra Airport used for handling domestic and international air traffic.
  • A. Runway 12/30
    Runway 12/30 is one of the primary paved runways used for aircraft takeoffs and landings at Washington Dulles International Airport in Virginia.
  • B. Runway 12/30
    Runway 12/30 is the primary paved runway used for commercial flight operations at L.F. Wade International Airport in Bermuda.
  • C. Runway 12/30
    Runway 12/30 is a primary paved runway at San Carlos Airport in California, used mainly for general aviation operations.
  • D. Runway 12/30
    Runway 12/30 is one of the primary paved runways at Chennai International Airport in India, used for handling both domestic and international air traffic.
  • E. Runway 12R/30L
    Runway 12R/30L is one of the primary paved runways used for aircraft takeoffs and landings at Nikola Tesla International Airport in Belgrade, Serbia.
  • 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_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0c1ecb081909051bcc1f38eea31 completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc51a7c6081909eeda563a4485e87 completed March 20, 2026, 10:07 p.m.
NEDg Description generation batch_69bdc93a17548190b7ee841b25f7ad13 completed March 20, 2026, 10:24 p.m.
NED2 Entity disambiguation (via description) batch_69bdc9b4f9ac8190ae15c6445748a66e completed March 20, 2026, 10:27 p.m.
Created at: March 8, 2026, 3:21 p.m.