Triple

T18621031
Position Surface form Disambiguated ID Type / Status
Subject RAF Ballykelly E455146 entity
Predicate hasIcaoCode P419 FINISHED
Object EGLK
EGLK is the ICAO airport code for RAF Ballykelly, a former Royal Air Force station in Northern Ireland.
 E1334513 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: EGLK | Statement: [RAF Ballykelly, hasIcaoCode, EGLK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EGLK
Context triple: [RAF Ballykelly, hasIcaoCode, EGLK]
  • A. EGL
    EGL is the station code used to identify Eglinton station in transit systems and related services.
  • B. EGL
    EGL is an interface between Khronos rendering APIs like OpenGL ES and the native windowing system, enabling efficient rendering and context management on a variety of platforms.
  • C. EGLC
    EGLC is the ICAO airport code for London City Airport, a central London hub known for its short runway and business-focused flights.
  • D. KGL
    KGL is the IATA airport code for Kigali International Airport, the main air gateway to Rwanda’s capital city.
  • E. EKL
    EKL is the abbreviation for the Estonian Defence League, a voluntary national defence organization supporting Estonia’s military and civil security.
  • 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: EGLK
Triple: [RAF Ballykelly, hasIcaoCode, EGLK]
Generated description
EGLK is the ICAO airport code for RAF Ballykelly, a former Royal Air Force station in Northern Ireland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EGLK
Target entity description: EGLK is the ICAO airport code for RAF Ballykelly, a former Royal Air Force station in Northern Ireland.
  • A. EGL
    EGL is the station code used to identify Eglinton station in transit systems and related services.
  • B. EGL
    EGL is an interface between Khronos rendering APIs like OpenGL ES and the native windowing system, enabling efficient rendering and context management on a variety of platforms.
  • C. EGLC
    EGLC is the ICAO airport code for London City Airport, a central London hub known for its short runway and business-focused flights.
  • D. KGL
    KGL is the IATA airport code for Kigali International Airport, the main air gateway to Rwanda’s capital city.
  • E. EKL
    EKL is the National Rail station code for East Kilbride railway station in South Lanarkshire, Scotland.
  • 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_69d8d38cc7948190a55ea64e5638994e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54f0146f48190a872032db6e660c6 completed April 19, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d7423d88190a8ec0f7f8b35a535 completed May 13, 2026, 11:47 p.m.
NEDg Description generation batch_6a050e7895508190b6f9d677acb97c64 completed May 13, 2026, 11:51 p.m.
NED2 Entity disambiguation (via description) batch_6a050f0dac088190a8455c7219e3c709 completed May 13, 2026, 11:53 p.m.
Created at: April 10, 2026, 11:46 a.m.