Triple

T3114819
Position Surface form Disambiguated ID Type / Status
Subject College Park Airport E65037 entity
Predicate hasICAOcode P419 FINISHED
Object KCGS
KCGS is the ICAO airport code for College Park Airport, a historic general aviation airfield located in College Park, Maryland, USA.
E327846 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: KCGS | Statement: [College Park Airport, hasICAOcode, KCGS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KCGS
Context triple: [College Park Airport, hasICAOcode, KCGS]
  • A. KCS
    KCS is the commonly used abbreviation for Knox County Schools, a public school district serving Knox County, Tennessee.
  • B. KSGH
    KSGH is the ICAO airport code for Springfield–Beckley Municipal Airport in Springfield, Ohio, United States.
  • C. Kokusai
    Kokusai was a Japanese aircraft manufacturer known for producing military and transport planes before and during World War II.
  • D. Kindai
    Kindai is a major private university in Japan known for its comprehensive academic programs and strong research in fields such as science, engineering, and fisheries.
  • E. KCA
    KCA is a nonprofit organization dedicated to providing life-saving HIV treatment, care, and support to children and families in underserved communities, particularly in Africa and India.
  • 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: KCGS
Triple: [College Park Airport, hasICAOcode, KCGS]
Generated description
KCGS is the ICAO airport code for College Park Airport, a historic general aviation airfield located in College Park, Maryland, USA.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KCGS
Target entity description: KCGS is the ICAO airport code for College Park Airport, a historic general aviation airfield located in College Park, Maryland, USA.
  • A. KCS
    KCS is the commonly used abbreviation for Knox County Schools, a public school district serving Knox County, Tennessee.
  • B. KSGH
    KSGH is the ICAO airport code for Springfield–Beckley Municipal Airport in Springfield, Ohio, United States.
  • C. Kokusai
    Kokusai was a Japanese aircraft manufacturer known for producing military and transport planes before and during World War II.
  • D. Kindai
    Kindai is a major private university in Japan known for its comprehensive academic programs and strong research in fields such as science, engineering, and fisheries.
  • E. KCA
    KCA is a nonprofit organization dedicated to providing life-saving HIV treatment, care, and support to children and families in underserved communities, particularly in Africa and India.
  • 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_69ad857fcc088190b0c4d45a5cde6f61 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada43dca688190ab041554220c5271 completed March 8, 2026, 4:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2039b11d4819095ee77d84d6e7b8a completed March 12, 2026, 12:06 a.m.
NEDg Description generation batch_69b20563abdc8190a51e1cfbcc6e0075 completed March 12, 2026, 12:14 a.m.
NED2 Entity disambiguation (via description) batch_69b205f1b3c08190a63fd9494dc8aee8 completed March 12, 2026, 12:16 a.m.
Created at: March 8, 2026, 3:04 p.m.