Triple

T3264627
Position Surface form Disambiguated ID Type / Status
Subject Sawyer International Airport E68494 entity
Predicate FAAcode P420 FINISHED
Object SAW
SAW is the FAA airport code for Sawyer International Airport, a public airport serving the Marquette region in Michigan, United States.
 E161448 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: [Sawyer International Airport, FAAcode, SAW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAW
Context triple: [Sawyer International Airport, FAAcode, SAW]
  • A. SAW
    SAW is the IATA airport code for Sabiha Gökçen International Airport, a major international airport serving Istanbul, Turkey.
  • B. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • C. SA4
    SA4 is a 3GPP working group responsible for the standardization of multimedia codecs, systems, and services in mobile communications.
  • D. SA2
    SA2 is a 3GPP working group responsible for defining the overall system architecture and functional specifications of mobile communication networks.
  • E. SAU
    SAU is an international university established by the South Asian Association for Regional Cooperation (SAARC) in New Delhi, India, focusing on postgraduate and doctoral education and research for students from South Asian countries.
  • 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: [Sawyer International Airport, FAAcode, SAW]
Generated description
SAW is the FAA airport code for Sawyer International Airport, a public airport serving the Marquette region in Michigan, United States.
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, a public airport serving the Marquette region in Michigan, United States.
  • A. SAW chosen
    SAW is the IATA airport code for Sabiha Gökçen International Airport, a major international airport serving Istanbul, Turkey.
  • B. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • C. SA4
    SA4 is a 3GPP working group responsible for the standardization of multimedia codecs, systems, and services in mobile communications.
  • D. SA2
    SA2 is a 3GPP working group responsible for defining the overall system architecture and functional specifications of mobile communication networks.
  • E. SAU
    SAU is an international university established by the South Asian Association for Regional Cooperation (SAARC) in New Delhi, India, focusing on postgraduate and doctoral education and research for students from South Asian countries.
  • F. None of above.

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_69ad8590444081909e8107a8aeef3a23 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adafcb2da08190a7f4fefdfe6d0098 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ee82a78819082582a24bac97f44 completed March 12, 2026, 10:01 a.m.
NEDg Description generation batch_69b29015e77481908c8b41fc3f75dd6f completed March 12, 2026, 10:06 a.m.
NED2 Entity disambiguation (via description) batch_69b2ac133f648190a4040881db05a353 completed March 12, 2026, 12:05 p.m.
Created at: March 8, 2026, 3:09 p.m.