Triple

T15550465
Position Surface form Disambiguated ID Type / Status
Subject K. I. Sawyer Air Force Base E370728 entity
Predicate hasFAAcode P420 FINISHED
Object SAW
SAW is the FAA airport code for Sawyer International Airport in Michigan, a public airport on the site of the former K. I. Sawyer Air Force Base.
 E1164434 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: SAW | Statement: [K. I. Sawyer Air Force Base, hasFAAcode, SAW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAW
Context triple: [K. I. Sawyer Air Force Base, hasFAAcode, SAW]
  • A. SAW
    SAW is the IATA airport code for Sabiha Gökçen International Airport, a major international airport serving Istanbul, Turkey.
  • B. SAW
    SAW is the abbreviation for the U.S. Marine Corps’ School of Advanced Warfighting, an advanced professional military education institution focused on developing operational-level planners and leaders.
  • C. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • D. SAV
    SAV is the National Rail station code for Stratford-upon-Avon railway station in Warwickshire, England.
  • E. SAV
    SAV is the IATA airport code for Savannah/Hilton Head International Airport serving Savannah, Georgia, and the surrounding region.
  • 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: SAW
Triple: [K. I. Sawyer Air Force Base, hasFAAcode, SAW]
Generated description
SAW is the FAA airport code for Sawyer International Airport in Michigan, a public airport on the site of the former K. I. Sawyer Air Force Base.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAW
Target entity description: SAW is the FAA airport code for Sawyer International Airport in Michigan, a public airport on the site of the former K. I. Sawyer Air Force Base.
  • A. SAW
    SAW is the IATA airport code for Sabiha Gökçen International Airport, a major international airport serving Istanbul, Turkey.
  • B. SAW
    SAW is the abbreviation for the U.S. Marine Corps’ School of Advanced Warfighting, an advanced professional military education institution focused on developing operational-level planners and leaders.
  • C. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • D. SAV
    SAV is the National Rail station code for Stratford-upon-Avon railway station in Warwickshire, England.
  • E. SAV
    SAV is the IATA airport code for Savannah/Hilton Head International Airport serving Savannah, Georgia, and the surrounding region.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a9551288190a583e8291c35f521 completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c3e67c881909a9fa1e483a364be completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff4d7e60dc8190aa80cb269b1811bc completed May 9, 2026, 3:06 p.m.
NED2 Entity disambiguation (via description) batch_69ff4e03e8748190a23e7577accaf04a completed May 9, 2026, 3:08 p.m.
Created at: April 10, 2026, 4:08 a.m.