Triple

T17922016
Position Surface form Disambiguated ID Type / Status
Subject Columbia County Airport E448095 entity
Predicate IATA code P2569 FINISHED
Object HCC
HCC is the three-letter IATA airport code assigned to Columbia County Airport in New York, United States.
E1296821 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: HCC | Statement: [Columbia County Airport, IATA code, HCC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HCC
Context triple: [Columbia County Airport, IATA code, HCC]
  • A. HCC
    HCC is an NCAA Division III athletic conference composed primarily of small colleges in the Midwestern United States.
  • B. HCC
    HCC is the stock ticker symbol for HCC Insurance Holdings, a specialty insurance company that provides a range of niche insurance products and services.
  • C. HFLD
    HFLD is a shorthand reference to Luke Bryan’s country song “Huntin’, Fishin’ and Lovin’ Every Day,” which celebrates an outdoors-oriented, small-town lifestyle.
  • D. HCCC
    HCCC is a Houston-based arts institution dedicated to advancing contemporary craft through exhibitions, artist residencies, and educational programs.
  • E. Canon cancrizans
    Canon cancrizans is a retrograde canon by Johann Sebastian Bach, best known as one of the intricate contrapuntal pieces in his *Musical Offering* (BWV 1079).
  • 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: HCC
Triple: [Columbia County Airport, IATA code, HCC]
Generated description
HCC is the three-letter IATA airport code assigned to Columbia County Airport in New York, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HCC
Target entity description: HCC is the three-letter IATA airport code assigned to Columbia County Airport in New York, United States.
  • A. HCC
    HCC is an NCAA Division III athletic conference composed primarily of small colleges in the Midwestern United States.
  • B. HCC
    HCC is the stock ticker symbol for HCC Insurance Holdings, a specialty insurance company that provides a range of niche insurance products and services.
  • C. HFLD
    HFLD is a shorthand reference to Luke Bryan’s country song “Huntin’, Fishin’ and Lovin’ Every Day,” which celebrates an outdoors-oriented, small-town lifestyle.
  • D. HCCC
    HCCC is a Houston-based arts institution dedicated to advancing contemporary craft through exhibitions, artist residencies, and educational programs.
  • E. Canon cancrizans
    Canon cancrizans is a retrograde canon by Johann Sebastian Bach, best known as one of the intricate contrapuntal pieces in his *Musical Offering* (BWV 1079).
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a30ad8748190b28d3e8b5afab2ef completed April 19, 2026, 9:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0321327e4c8190bdc90976312a9913 completed May 12, 2026, 12:46 p.m.
NEDg Description generation batch_6a032313086c8190b3c6c657a98942c0 completed May 12, 2026, 12:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0323f4a2c48190914075393ab1aca7 completed May 12, 2026, 12:58 p.m.
Created at: April 10, 2026, 10:20 a.m.