Triple

T19839557
Position Surface form Disambiguated ID Type / Status
Subject San Antonio International Airport E476688 entity
Predicate runway P1654 FINISHED
Object 13L/31R
13L/31R is a primary paved runway at San Antonio International Airport used for commercial and general aviation takeoffs and landings.
E1398626 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: 13L/31R | Statement: [San Antonio International Airport, runway, 13L/31R]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 13L/31R
Context triple: [San Antonio International Airport, runway, 13L/31R]
  • A. 13R/31L
    13R/31L is a major runway at Dallas/Fort Worth International Airport used for handling high volumes of commercial air traffic.
  • B. 01L/19R
    01L/19R is one of the primary paved runways at New Chitose Airport in Hokkaido, Japan, used for handling commercial air traffic.
  • C. 15R/33L
    15R/33L is a primary north–south runway at George Bush Intercontinental Airport in Houston, Texas, used for both arrivals and departures of commercial air traffic.
  • D. 12R/30L
    12R/30L is a primary paved runway at St. Louis Lambert International Airport used for aircraft takeoffs and landings.
  • E. 10L/28R
    10L/28R is a primary east–west runway at Port Columbus International Airport used for commercial aircraft operations.
  • 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: 13L/31R
Triple: [San Antonio International Airport, runway, 13L/31R]
Generated description
13L/31R is a primary paved runway at San Antonio International Airport used for commercial and general aviation takeoffs and landings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 13L/31R
Target entity description: 13L/31R is a primary paved runway at San Antonio International Airport used for commercial and general aviation takeoffs and landings.
  • A. 13R/31L
    13R/31L is a major runway at Dallas/Fort Worth International Airport used for handling high volumes of commercial air traffic.
  • B. 01L/19R
    01L/19R is one of the primary paved runways at New Chitose Airport in Hokkaido, Japan, used for handling commercial air traffic.
  • C. 15R/33L
    15R/33L is a primary north–south runway at George Bush Intercontinental Airport in Houston, Texas, used for both arrivals and departures of commercial air traffic.
  • D. 12R/30L
    12R/30L is a primary paved runway at St. Louis Lambert International Airport used for aircraft takeoffs and landings.
  • E. 10L/28R
    10L/28R is a primary east–west runway at Port Columbus International Airport used for commercial aircraft 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65804be608190b49e110c3bf381bc completed April 20, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07d436990481908bb488d3935fa773 completed May 16, 2026, 2:19 a.m.
NEDg Description generation batch_6a07d5ec45208190a75365a4a411aa7c completed May 16, 2026, 2:26 a.m.
NED2 Entity disambiguation (via description) batch_6a07d6ffc6508190aa9df66c2cf3d532 completed May 16, 2026, 2:31 a.m.
Created at: April 10, 2026, 1:50 p.m.