Triple

T20962623
Position Surface form Disambiguated ID Type / Status
Subject Kiel-Holtenau Airport E516285 entity
Predicate IATA code P2569 FINISHED
Object KEL
KEL is the IATA airport code for Kiel-Holtenau Airport, a regional airport serving the city of Kiel in northern Germany.
 E1459819 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: KEL | Statement: [Kiel-Holtenau Airport, IATA code, KEL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KEL
Context triple: [Kiel-Holtenau Airport, IATA code, KEL]
  • A. KELM
    KELM is the ICAO airport code for Elmira/Corning Regional Airport, a public airport serving the Elmira–Corning area in New York, United States.
  • B. KLE
    KLE is the vehicle registration code for the district of Cleves (Kleve) in the German state of North Rhine-Westphalia.
  • C. KL
    KL is the abbreviation commonly used for the Royal Netherlands Army, the land forces branch of the Dutch Armed Forces.
  • D. KL
    KL is the squadron code historically used to identify No. 54 Squadron of the Royal Air Force on its aircraft and operational records.
  • E. KL
    KL is the station code used to identify the Berlin U-Bahn station Krumme Lanke.
  • 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: KEL
Triple: [Kiel-Holtenau Airport, IATA code, KEL]
Generated description
KEL is the IATA airport code for Kiel-Holtenau Airport, a regional airport serving the city of Kiel in northern Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KEL
Target entity description: KEL is the IATA airport code for Kiel-Holtenau Airport, a regional airport serving the city of Kiel in northern Germany.
  • A. KELM
    KELM is the ICAO airport code for Elmira/Corning Regional Airport, a public airport serving the Elmira–Corning area in New York, United States.
  • B. KLE
    KLE is the vehicle registration code for the district of Cleves (Kleve) in the German state of North Rhine-Westphalia.
  • C. KL
    KL is the two-letter IATA airline code assigned to KLM Royal Dutch Airlines.
  • D. KL
    KL is the official vehicle registration code assigned to the Indian state of Kerala.
  • E. KL
    KL is the abbreviation commonly used for the Royal Netherlands Army, the land forces branch of the Dutch Armed Forces.
  • 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_69e0b4fde6c48190af1398e7e734629e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fb710d6c8190a2daacaad3b22683 completed April 21, 2026, 4:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092798800481909d437b58467f8e2b completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a0928b4be448190bd862c8f971e61d9 completed May 17, 2026, 2:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0929734a5c8190911e54b601118bae completed May 17, 2026, 2:35 a.m.
Created at: April 16, 2026, 1:32 p.m.