Triple

T17285934
Position Surface form Disambiguated ID Type / Status
Subject Skardu Airport E419654 entity
Predicate hasRunway P105 FINISHED
Object Runway 14L/32R — NE ONDG

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 14L/32R | Statement: [Skardu Airport, hasRunway, Runway 14L/32R]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 14L/32R
Context triple: [Skardu Airport, hasRunway, Runway 14L/32R]
  • A. Runway 14L/32R
    Runway 14L/32R is one of the primary paved runways at Moffett Field in California, used for military, research, and general aviation operations.
  • B. Runway 14L/32R
    Runway 14L/32R is a principal paved runway used for aircraft takeoffs and landings at Jacksons International Airport in Papua New Guinea.
  • C. Runway 14L/32R
    Runway 14L/32R is a primary military runway at Naval Air Station Lemoore used for U.S. Navy flight operations and training.
  • D. Runway 14L/32R
    Runway 14L/32R is one of the primary paved runways at Toulouse-Blagnac Airport in France, used for commercial and test flight operations.
  • E. Runway 14R/32L
    Runway 14R/32L is a primary paved runway at Moscow’s Domodedovo International Airport 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 14L/32R
Triple: [Skardu Airport, hasRunway, Runway 14L/32R]
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 14L/32R
Target entity description: Runway 14L/32R is a principal runway at Skardu Airport in Pakistan, serving as a key facility for handling domestic and tourist air traffic to the mountainous Gilgit-Baltistan region.
  • A. Runway 14L/32R
    Runway 14L/32R is one of the primary paved runways at Moffett Field in California, used for military, research, and general aviation operations.
  • B. Runway 14L/32R
    Runway 14L/32R is one of the primary paved runways at Toulouse-Blagnac Airport in France, used for commercial and test flight operations.
  • C. Runway 14L/32R
    Runway 14L/32R is a principal paved runway used for aircraft takeoffs and landings at Jacksons International Airport in Papua New Guinea.
  • D. Runway 14L/32R
    Runway 14L/32R is a primary military runway at Naval Air Station Lemoore used for U.S. Navy flight operations and training.
  • E. Runway 14R/32L
    Runway 14R/32L is a primary paved runway at Moscow’s Domodedovo International Airport used for handling commercial air traffic.
  • F. None of above. chosen

Provenance (4 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_69d886db32608190a61e18862c5a8af6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e4378024988190aac6aec006f8f7a1 completed April 19, 2026, 2:01 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0195488d2c81908ac6c19f54f61796 completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a01965807cc819088792a88b8a099d3 in_progress May 11, 2026, 8:42 a.m.
Created at: April 10, 2026, 5:40 a.m.