Triple

T13128961
Position Surface form Disambiguated ID Type / Status
Subject Marina Municipal Airport E311916 entity
Predicate ICAO code P419 FINISHED
Object KOAR
KOAR is the ICAO airport code for Marina Municipal Airport in Marina, California.
 E1023278 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: KOAR | Statement: [Marina Municipal Airport, ICAO code, KOAR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KOAR
Context triple: [Marina Municipal Airport, ICAO code, KOAR]
  • A. KOA
    KOA is the three-letter IATA airport code for Kona International Airport on the island of Hawaiʻi.
  • B. KOAK
    KOAK is the ICAO airport code for Oakland International Airport, a major commercial and cargo airport serving the San Francisco Bay Area in California.
  • C. KO
    KO is the line symbol used to represent the Keiō New Line, a railway line in the Tokyo metropolitan area operated by Keio Corporation.
  • D. KO
    KO is the New York Stock Exchange ticker symbol for The Coca-Cola Company, one of the world’s largest and most recognizable beverage corporations.
  • E. KA
    KA is a postcode area in the United Kingdom covering parts of southwest Scotland, including towns such as Kilmarnock and Irvine.
  • 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: KOAR
Triple: [Marina Municipal Airport, ICAO code, KOAR]
Generated description
KOAR is the ICAO airport code for Marina Municipal Airport in Marina, California.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KOAR
Target entity description: KOAR is the ICAO airport code for Marina Municipal Airport in Marina, California.
  • A. KOA
    KOA is the three-letter IATA airport code for Kona International Airport on the island of Hawaiʻi.
  • B. KOAK
    KOAK is the ICAO airport code for Oakland International Airport, a major commercial and cargo airport serving the San Francisco Bay Area in California.
  • C. KO
    KO is the New York Stock Exchange ticker symbol for The Coca-Cola Company, one of the world’s largest and most recognizable beverage corporations.
  • D. KO
    KO is the line symbol used to represent the Keiō New Line, a railway line in the Tokyo metropolitan area operated by Keio Corporation.
  • E. KA
    KA is the vehicle registration code used on license plates for cars registered in the German city of Karlsruhe.
  • 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_69d806a9fe888190b081e2d9ea665d6c completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9819bfd348190a22d44f837877e1c completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e28e922881909584296adc95d9b4 completed May 3, 2026, 5:52 a.m.
NEDg Description generation batch_69f6e6d4aedc819090e6433600db4b31 completed May 3, 2026, 6:10 a.m.
NED2 Entity disambiguation (via description) batch_69f6e79e40bc8190bcf72d719d4e88dd completed May 3, 2026, 6:13 a.m.
Created at: April 9, 2026, 9:07 p.m.