Triple

T11550962
Position Surface form Disambiguated ID Type / Status
Subject South Bend International Airport E273887 entity
Predicate hasRunway P105 FINISHED
Object Runway 18/36
Runway 18/36 is a primary north–south runway at South Bend International Airport used for takeoffs and landings of various aircraft.
 E960035 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 18/36 | Statement: [South Bend International Airport, hasRunway, Runway 18/36]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 18/36
Context triple: [South Bend International Airport, hasRunway, Runway 18/36]
  • A. Runway 18/36
    Runway 18/36 is a primary paved runway at Monroe Regional Airport in Louisiana, used for commercial and general aviation takeoffs and landings.
  • B. Runway 18/36
    Runway 18/36 is a primary paved runway at Council Bluffs Municipal Airport used for general aviation takeoffs and landings.
  • C. Runway 18/36
    Runway 18/36 is a primary north–south oriented runway used for military aviation operations at RAAF Base Edinburgh in South Australia.
  • D. Runway 18/36
    Runway 18/36 is a primary paved runway at Turin Airport in Italy, used for both commercial and general aviation operations.
  • E. Runway 18/36
    Runway 18/36 is a primary paved runway at Ürümqi Diwopu International Airport in Xinjiang, China, used for handling commercial 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 18/36
Triple: [South Bend International Airport, hasRunway, Runway 18/36]
Generated description
Runway 18/36 is a primary north–south runway at South Bend International Airport used for takeoffs and landings of various aircraft.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 18/36
Target entity description: Runway 18/36 is a primary north–south runway at South Bend International Airport used for takeoffs and landings of various aircraft.
  • A. Runway 18/36
    Runway 18/36 is a primary paved runway at Council Bluffs Municipal Airport used for general aviation takeoffs and landings.
  • B. Runway 18/36
    Runway 18/36 is a primary paved runway at Monroe Regional Airport in Louisiana, used for commercial and general aviation takeoffs and landings.
  • C. Runway 18/36
    Runway 18/36 is a primary military runway at Naval Air Station North Island in California, used for operations by U.S. Navy aircraft.
  • D. Runway 18/36
    Runway 18/36 is the primary north–south runway used for takeoffs and landings at Chiang Mai International Airport in northern Thailand.
  • E. Runway 18/36
    Runway 18/36 is a primary paved runway at Turin Airport in Italy, used for both 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88a83f1e88190aabf11a4c8a6c9e5 completed April 10, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69f489dfb2c881908a6f6bcd8b2d1cdc completed May 1, 2026, 11:09 a.m.
NEDg Description generation batch_69f48fc3baac8190af87b55164f00b26 completed May 1, 2026, 11:34 a.m.
NED2 Entity disambiguation (via description) batch_69f495ab52788190a886f7014267f8e2 completed May 1, 2026, 11:59 a.m.
Created at: April 8, 2026, 9:37 p.m.