Triple

T19425360
Position Surface form Disambiguated ID Type / Status
Subject Merrill Field E485965 entity
Predicate hasRunway P105 FINISHED
Object Runway 5/23
Runway 5/23 is a primary paved runway at Merrill Field Airport in Anchorage, Alaska, used mainly for general aviation operations.
 E1390641 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 5/23 | Statement: [Merrill Field, hasRunway, Runway 5/23]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Runway 5/23
Context triple: [Merrill Field, hasRunway, Runway 5/23]
  • A. Runway 5/23
    Runway 5/23 is a primary paved runway at Molokai Airport in Hawaii, used for handling the airport’s main commercial and general aviation traffic.
  • B. Runway 5/23
    Runway 5/23 is a primary paved runway at Middle Georgia Regional Airport used for takeoffs and landings by general aviation and commercial aircraft.
  • C. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Indianapolis International Airport used for commercial and cargo aircraft operations.
  • D. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Willow Run Airport in Michigan, used mainly for cargo and general aviation operations.
  • E. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Rickenbacker International Airport in Ohio, used for handling large commercial and cargo 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: Runway 5/23
Triple: [Merrill Field, hasRunway, Runway 5/23]
Generated description
Runway 5/23 is a primary paved runway at Merrill Field Airport in Anchorage, Alaska, used mainly for general aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Runway 5/23
Target entity description: Runway 5/23 is a primary paved runway at Merrill Field Airport in Anchorage, Alaska, used mainly for general aviation operations.
  • A. Runway 5/23
    Runway 5/23 is a primary paved runway at Molokai Airport in Hawaii, used for handling the airport’s main commercial and general aviation traffic.
  • B. Runway 5/23
    Runway 5/23 is a primary paved runway at Middle Georgia Regional Airport used for takeoffs and landings by general aviation and commercial aircraft.
  • C. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Indianapolis International Airport used for commercial and cargo aircraft operations.
  • D. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Willow Run Airport in Michigan, used mainly for cargo and general aviation operations.
  • E. Runway 5R/23L
    Runway 5R/23L is a primary paved runway at Rickenbacker International Airport in Ohio, used for handling large commercial and cargo 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63218772c8190a48b6cb01bd12b73 completed April 20, 2026, 2:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ab7e0d4081909296ab9498e7996f completed May 15, 2026, 11:25 p.m.
NEDg Description generation batch_6a07acb892408190bd5e927cad3343ec completed May 15, 2026, 11:31 p.m.
NED2 Entity disambiguation (via description) batch_6a07ad2377488190b4f52c72a9a5d196 completed May 15, 2026, 11:32 p.m.
Created at: April 10, 2026, 1:37 p.m.