Triple

T11382271
Position Surface form Disambiguated ID Type / Status
Subject Dubrovnik Airport E269624 entity
Predicate hasRunway P105 FINISHED
Object Runway 12/30
Runway 12/30 is a primary paved runway at Dubrovnik Airport in Croatia, used for handling both domestic and international air traffic.
E949790 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: [Dubrovnik Airport, hasRunway, Runway 12/30]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Runway 12/30
Context triple: [Dubrovnik Airport, hasRunway, Runway 12/30]
  • A. Runway 12/30
    Runway 12/30 is a principal runway at Cairns Airport in Queensland, Australia, used for both domestic and international aircraft operations.
  • B. Runway 12/30
    Runway 12/30 is a principal paved runway at Ambala Air Force Station in Haryana, India, used for military flight operations.
  • C. Runway 12/30
    Runway 12/30 is a primary paved runway at Garden City Regional Airport in Kansas, used for handling the airport’s commercial and general aviation traffic.
  • D. Runway 12/30
    Runway 12/30 is a principal paved runway at Brest Airport in France, aligned roughly southeast–northwest to accommodate prevailing winds and commercial air traffic.
  • E. Runway 12/30
    Runway 12/30 is a primary paved runway at Brewton Municipal Airport in Alabama, used for general aviation takeoffs and landings aligned roughly southeast–northwest.
  • 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: [Dubrovnik Airport, hasRunway, Runway 12/30]
Generated description
Runway 12/30 is a primary paved runway at Dubrovnik Airport in Croatia, used for handling both 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 primary paved runway at Dubrovnik Airport in Croatia, used for handling both domestic and international air traffic.
  • A. Runway 12/30
    Runway 12/30 is a principal paved runway at Canberra Airport used for handling domestic and international air traffic.
  • B. 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.
  • C. Runway 12/30
    Runway 12/30 is a principal paved runway at Málaga Airport in southern Spain, used for handling a large volume of commercial air traffic.
  • D. Runway 12/30
    Runway 12/30 is a principal runway at Cairns Airport in Queensland, Australia, used for both domestic and international aircraft operations.
  • E. Runway 12/30
    Runway 12/30 is a primary paved runway at Edmonton International Airport used for handling a wide range of commercial and general aviation traffic.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7fc331f188190a7f69f1aae53fb6b completed April 9, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f165cc34608190b6a00aa120199eff completed April 29, 2026, 1:58 a.m.
NEDg Description generation batch_69f170034b488190a6976d3333823caa completed April 29, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_69f17805325881908b98eb9c8fc59778 completed April 29, 2026, 3:16 a.m.
Created at: April 8, 2026, 9:34 p.m.