Triple

T16069546
Position Surface form Disambiguated ID Type / Status
Subject East London Airport E389823 entity
Predicate ICAOcode P419 FINISHED
Object FAEL
FAEL is the ICAO airport code for East London Airport, a regional airport serving the city of East London in South Africa.
 E459943 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: FAEL | Statement: [East London Airport, ICAOcode, FAEL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FAEL
Context triple: [East London Airport, ICAOcode, FAEL]
  • A. FAE
    FAE is the IATA airport code for Vágar Airport, the main international gateway to the Faroe Islands.
  • B. FAE
    FAE is the acronym for the Ecuadorian Air Force, the aerial warfare branch of Ecuador’s military responsible for defending the nation’s airspace.
  • C. FALE
    FALE is the ICAO airport code assigned to King Shaka International Airport in Durban, South Africa.
  • D. FAES
    FAES is the acronym for the Armed Forces of El Salvador, the country's unified military institution responsible for national defense and security.
  • E. FALA
    FALA is the ICAO airport code for Lanseria International Airport, a major privately owned international airport serving the Johannesburg region in South Africa.
  • 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: FAEL
Triple: [East London Airport, ICAOcode, FAEL]
Generated description
FAEL is the ICAO airport code for East London Airport, a regional airport serving the city of East London in South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FAEL
Target entity description: FAEL is the ICAO airport code for East London Airport, a regional airport serving the city of East London in South Africa.
  • A. FAE
    FAE is the IATA airport code for Vágar Airport, the main international gateway to the Faroe Islands.
  • B. FAE
    FAE is the acronym for the Ecuadorian Air Force, the aerial warfare branch of Ecuador’s military responsible for defending the nation’s airspace.
  • C. FALE chosen
    FALE is the ICAO airport code assigned to King Shaka International Airport in Durban, South Africa.
  • D. FAES
    FAES is the acronym for the Armed Forces of El Salvador, the country's unified military institution responsible for national defense and security.
  • E. FALA
    FALA is the ICAO airport code for Lanseria International Airport, a major privately owned international airport serving the Johannesburg region in South Africa.
  • F. None of above.

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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183bd9578819097e7cb1108b1f6f7 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe4827cd48190aa470c6537e72508 completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe6c956a48190845faac983b9a064 completed May 10, 2026, 2 a.m.
NED2 Entity disambiguation (via description) batch_69ffe7387b38819094e55ae14ec2c036 completed May 10, 2026, 2:02 a.m.
Created at: April 10, 2026, 4:57 a.m.