Triple

T7923649
Position Surface form Disambiguated ID Type / Status
Subject Anholt E184005 entity
Predicate hasAirportICAO P419 FINISHED
Object EKAT
EKAT is the ICAO airport code for Anholt Airport, a small airfield serving the Danish island of Anholt in the Kattegat Sea.
 E698024 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: EKAT | Statement: [Anholt, hasAirportICAO, EKAT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EKAT
Context triple: [Anholt, hasAirportICAO, EKAT]
  • A. EKM
    EKM is a Protestant regional church body in Germany that forms part of the Evangelical Church in Germany (EKD).
  • B. KAT
    KAT is the public transportation system serving Knoxville, Tennessee, operating local bus and transit services throughout the city and surrounding areas.
  • C. Ek
    Ek is a Swedish surname borne by several notable figures, including politicians and entrepreneurs.
  • D. EK
    EK is the commonly used abbreviation for the First Chamber of the Austrian Parliament (Erste Kammer).
  • E. EK
    EK was the New York Stock Exchange ticker symbol for Eastman Kodak Company, the historic American photography and imaging corporation.
  • 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: EKAT
Triple: [Anholt, hasAirportICAO, EKAT]
Generated description
EKAT is the ICAO airport code for Anholt Airport, a small airfield serving the Danish island of Anholt in the Kattegat Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EKAT
Target entity description: EKAT is the ICAO airport code for Anholt Airport, a small airfield serving the Danish island of Anholt in the Kattegat Sea.
  • A. EKM
    EKM is a Protestant regional church body in Germany that forms part of the Evangelical Church in Germany (EKD).
  • B. KAT
    KAT is the public transportation system serving Knoxville, Tennessee, operating local bus and transit services throughout the city and surrounding areas.
  • C. Ek
    Ek is a Swedish surname borne by several notable figures, including politicians and entrepreneurs.
  • D. EK
    EK was the New York Stock Exchange ticker symbol for Eastman Kodak Company, the historic American photography and imaging corporation.
  • E. EK
    EK is the commonly used abbreviation for the First Chamber of the Austrian Parliament (Erste Kammer).
  • 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_69ca828fe7bc819090f52c88dcd72183 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3aac02bc8190b13fc354a4fa91d3 completed March 31, 2026, 3:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5bf3c3288190ac3df917be92f9f8 completed March 31, 2026, 5:30 a.m.
NEDg Description generation batch_69cb5f222c808190b9ef39896f149278 completed March 31, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69cb76c896c08190a67a5b572436f2d9 completed March 31, 2026, 7:24 a.m.
Created at: March 30, 2026, 5:06 p.m.