Triple

T20604096
Position Surface form Disambiguated ID Type / Status
Subject HLZ E506256 entity
Predicate hasRunway P105 FINISHED
Object Runway 18L/36R
Runway 18L/36R is a primary paved runway at Hamilton Airport in New Zealand, used for commercial and general aviation operations.
 E1449281 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 18L/36R | Statement: [HLZ, hasRunway, Runway 18L/36R]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 18L/36R
Context triple: [HLZ, hasRunway, Runway 18L/36R]
  • A. Runway 18L/36R
    Runway 18L/36R is a primary north–south runway used for commercial air traffic at Orlando International Airport in Orlando, Florida.
  • B. Runway 18L/36R
    Runway 18L/36R is a primary paved runway used for aircraft takeoffs and landings at Shanghai Hongqiao International Airport.
  • C. Runway 18L/36R
    Runway 18L/36R is a primary north–south runway at Memphis International Airport used for both passenger and cargo aircraft operations.
  • D. Runway 18L/36R
    Runway 18L/36R is a primary paved runway at Boryspil International Airport near Kyiv, Ukraine, used for handling commercial air traffic.
  • E. Runway 18L/36R
    Runway 18L/36R is one of the primary paved runways at Antalya Airport in Turkey, 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 18L/36R
Triple: [HLZ, hasRunway, Runway 18L/36R]
Generated description
Runway 18L/36R is a primary paved runway at Hamilton Airport in New Zealand, used for commercial and general aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 18L/36R
Target entity description: Runway 18L/36R is a primary paved runway at Hamilton Airport in New Zealand, used for commercial and general aviation operations.
  • A. Runway 18L/36R
    Runway 18L/36R is a primary north–south runway used for commercial air traffic at Orlando International Airport in Orlando, Florida.
  • B. Runway 18L/36R
    Runway 18L/36R is a primary paved runway used for aircraft takeoffs and landings at Shanghai Hongqiao International Airport.
  • C. Runway 18L/36R
    Runway 18L/36R is a primary north–south runway at Memphis International Airport used for both passenger and cargo aircraft operations.
  • D. Runway 18L/36R
    Runway 18L/36R is a primary paved runway at Boryspil International Airport near Kyiv, Ukraine, used for handling commercial air traffic.
  • E. Runway 18L/36R
    Runway 18L/36R is one of the primary paved runways at Antalya Airport in Turkey, used for handling commercial air 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa233e1881908749d2f29c2946e4 completed April 20, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08ef742d9c8190839585ba6997d858 completed May 16, 2026, 10:28 p.m.
NEDg Description generation batch_6a08f118c3e88190ac42eef9b7ebb359 completed May 16, 2026, 10:35 p.m.
NED2 Entity disambiguation (via description) batch_6a08f14afe2881908995b095013c49e8 completed May 16, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:41 a.m.