Triple

T15985632
Position Surface form Disambiguated ID Type / Status
Subject Karup Air Base E387684 entity
Predicate ICAOcode P419 FINISHED
Object EKKA
EKKA is the ICAO airport code assigned to Karup Air Base in Denmark.
 E1187862 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: EKKA | Statement: [Karup Air Base, ICAOcode, EKKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EKKA
Context triple: [Karup Air Base, ICAOcode, EKKA]
  • A. EKKA
    EKKA was a Greek World War II resistance organization that played a significant role in the anti-Axis struggle and post-liberation political developments.
  • B. EYKA
    EYKA is the ICAO airport code for Kaunas Airport, an international airport serving the city of Kaunas in Lithuania.
  • C. EGKA
    EGKA is the ICAO airport code for Shoreham Airport, a general aviation airfield on the south coast of England.
  • D. Eke
    Eke is a town in the Okpokwu Local Government Area of Benue State, Nigeria.
  • E. EKO
    EKO is the three-letter IATA airport code for Elko Regional Airport, a public airport serving Elko, Nevada, in the United States.
  • 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: EKKA
Triple: [Karup Air Base, ICAOcode, EKKA]
Generated description
EKKA is the ICAO airport code assigned to Karup Air Base in Denmark.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EKKA
Target entity description: EKKA is the ICAO airport code assigned to Karup Air Base in Denmark.
  • A. EKKA
    EKKA was a Greek World War II resistance organization that played a significant role in the anti-Axis struggle and post-liberation political developments.
  • B. EYKA
    EYKA is the ICAO airport code for Kaunas Airport, an international airport serving the city of Kaunas in Lithuania.
  • C. EGKA
    EGKA is the ICAO airport code for Shoreham Airport, a general aviation airfield on the south coast of England.
  • D. Eke
    Eke is a town in the Okpokwu Local Government Area of Benue State, Nigeria.
  • E. EKO
    EKO is the three-letter IATA airport code for Elko Regional Airport, a public airport serving Elko, Nevada, in the United States.
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157589d78819091f7b9b1081dd6ad completed April 16, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3cfc8d08190a02abc90c889c8e1 completed May 9, 2026, 11:31 p.m.
NEDg Description generation batch_69ffc4ed71648190983a0a4150c4d8c4 completed May 9, 2026, 11:36 p.m.
NED2 Entity disambiguation (via description) batch_69ffc5a5b46881908589fd1dabef5378 completed May 9, 2026, 11:39 p.m.
Created at: April 10, 2026, 4:54 a.m.