Triple

T6023672
Position Surface form Disambiguated ID Type / Status
Subject Lihue Airport E134122 entity
Predicate runway P1654 FINISHED
Object Runway 17/35
Runway 17/35 is a primary paved runway at Lihue Airport on the Hawaiian island of Kauai, used for both commercial and general aviation operations.
 E644959 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 17/35 | Statement: [Lihue Airport, runway, Runway 17/35]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 17/35
Context triple: [Lihue Airport, runway, Runway 17/35]
  • A. Runway 17/35
    Runway 17/35 is a primary paved runway used for aircraft operations at Kauhava Air Base in Finland.
  • B. Runway 17/35
    Runway 17/35 is a primary paved runway at Fort Worth Meacham International Airport used for general aviation and regional air traffic operations.
  • C. Runway 17/35
    Runway 17/35 is a primary paved runway at Corvallis Municipal Airport in Oregon, used for general aviation and regional air traffic operations.
  • D. Runway 17/35
    Runway 17/35 is a primary paved runway at Pueblo Memorial Airport in Colorado, used for both general aviation and military training operations.
  • E. Runway 17/35
    Runway 17/35 is a primary paved runway used for aircraft takeoffs and landings at Ministro Pistarini International Airport near Buenos Aires, Argentina.
  • 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 17/35
Triple: [Lihue Airport, runway, Runway 17/35]
Generated description
Runway 17/35 is a primary paved runway at Lihue Airport on the Hawaiian island of Kauai, used for both commercial and general aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 17/35
Target entity description: Runway 17/35 is a primary paved runway at Lihue Airport on the Hawaiian island of Kauai, used for both commercial and general aviation operations.
  • A. Runway 17/35
    Runway 17/35 is a primary paved runway used for aircraft operations at Kauhava Air Base in Finland.
  • B. Runway 17/35
    Runway 17/35 is a primary paved runway at Fort Worth Meacham International Airport used for general aviation and regional air traffic operations.
  • C. Runway 17/35
    Runway 17/35 is a primary paved runway at Corvallis Municipal Airport in Oregon, used for general aviation and regional air traffic operations.
  • D. Runway 17/35
    Runway 17/35 is a primary paved runway at Pueblo Memorial Airport in Colorado, used for both general aviation and military training operations.
  • E. Runway 17/35
    Runway 17/35 is a primary paved runway at Parry Sound Area Municipal Airport in Ontario, Canada, used for general aviation and regional air traffic 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_69c008742a5c8190b9cb9c2787a3d8b3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04fbd7978819085d683578bc62aa3 completed March 22, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7ad5851b481908242f6d88a78a08a completed March 28, 2026, 10:28 a.m.
NEDg Description generation batch_69c7ae5767408190860c1c7bc3a769fa completed March 28, 2026, 10:32 a.m.
NED2 Entity disambiguation (via description) batch_69c7aeb68c3481909c6dff8ee51349ab completed March 28, 2026, 10:34 a.m.
Created at: March 22, 2026, 4:07 p.m.