Triple

T6978647
Position Surface form Disambiguated ID Type / Status
Subject Syracuse Hancock International Airport E161779 entity
Predicate ICAOcode P419 FINISHED
Object KSYR
KSYR is the ICAO airport code for Syracuse Hancock International Airport, a public airport serving Syracuse, New York.
E633594 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: KSYR | Statement: [Syracuse Hancock International Airport, ICAOcode, KSYR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KSYR
Context triple: [Syracuse Hancock International Airport, ICAOcode, KSYR]
  • A. KMSY
    KMSY is the ICAO airport code for Louis Armstrong New Orleans International Airport, the primary commercial airport serving the New Orleans metropolitan area in Louisiana, USA.
  • B. KSRQ
    KSRQ is the ICAO airport code for Sarasota–Bradenton International Airport, a commercial airport serving the Sarasota and Bradenton region on Florida’s Gulf Coast.
  • C. KSVN
    KSVN is the ICAO airport code for Hunter Army Airfield, a U.S. Army military airfield located in Savannah, Georgia.
  • D. KRDG
    KRDG is the ICAO airport code for Reading Regional Airport, a public airport serving Reading, Pennsylvania, in the United States.
  • E. KSAZ-TV
    KSAZ-TV is a Fox-affiliated television station serving the Phoenix, Arizona market.
  • 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: KSYR
Triple: [Syracuse Hancock International Airport, ICAOcode, KSYR]
Generated description
KSYR is the ICAO airport code for Syracuse Hancock International Airport, a public airport serving Syracuse, New York.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KSYR
Target entity description: KSYR is the ICAO airport code for Syracuse Hancock International Airport, a public airport serving Syracuse, New York.
  • A. KMSY
    KMSY is the ICAO airport code for Louis Armstrong New Orleans International Airport, the primary commercial airport serving the New Orleans metropolitan area in Louisiana, USA.
  • B. KSRQ
    KSRQ is the ICAO airport code for Sarasota–Bradenton International Airport, a commercial airport serving the Sarasota and Bradenton region on Florida’s Gulf Coast.
  • C. KSVN
    KSVN is the ICAO airport code for Hunter Army Airfield, a U.S. Army military airfield located in Savannah, Georgia.
  • D. KRDG
    KRDG is the ICAO airport code for Reading Regional Airport, a public airport serving Reading, Pennsylvania, in the United States.
  • E. KSAZ-TV
    KSAZ-TV is a Fox-affiliated television station serving the Phoenix, Arizona market.
  • 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_69c68855dc0481909b4c7e9e9ed273db completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db6aa6188190af7656ff4d0e3230 completed March 27, 2026, 7:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761b614e88190877455edd5f64cf1 completed March 28, 2026, 5:05 a.m.
NEDg Description generation batch_69c7629031608190b1ef76e969c97925 completed March 28, 2026, 5:09 a.m.
NED2 Entity disambiguation (via description) batch_69c76329a47081909b47894ba0e1cad1 completed March 28, 2026, 5:12 a.m.
Created at: March 27, 2026, 2:31 p.m.