Triple

T4686264
Position Surface form Disambiguated ID Type / Status
Subject King Shaka International Airport E103927 entity
Predicate IATAcode P418 FINISHED
Object DUR
DUR is the IATA airport code for King Shaka International Airport serving Durban, South Africa.
 E459942 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: DUR | Statement: [King Shaka International Airport, IATAcode, DUR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DUR
Context triple: [King Shaka International Airport, IATAcode, DUR]
  • A. DURL
    DURL is the abbreviated name of the Dubai Rapid Link consortium, a group formed to develop and operate parts of Dubai’s urban rail transit system.
  • B. DOR
    DOR is the standard abbreviation used for the Mexican football club Dorados de Sinaloa.
  • C. DOR
    DOR is the vehicle registration code used on license plates for the English county of Dorset.
  • D. DUS
    DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
  • E. DURIP
    DURIP is a U.S. Department of Defense funding program that provides universities with advanced research instrumentation to support cutting-edge defense-related science and engineering.
  • 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: DUR
Triple: [King Shaka International Airport, IATAcode, DUR]
Generated description
DUR is the IATA airport code for King Shaka International Airport serving Durban, South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DUR
Target entity description: DUR is the IATA airport code for King Shaka International Airport serving Durban, South Africa.
  • A. DURL
    DURL is the abbreviated name of the Dubai Rapid Link consortium, a group formed to develop and operate parts of Dubai’s urban rail transit system.
  • B. DOR
    DOR is the standard abbreviation used for the Mexican football club Dorados de Sinaloa.
  • C. DOR
    DOR is the vehicle registration code used on license plates for the English county of Dorset.
  • D. DUS
    DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
  • E. DURIP
    DURIP is a U.S. Department of Defense funding program that provides universities with advanced research instrumentation to support cutting-edge defense-related science and engineering.
  • 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_69bd43debbf08190b4bc372e286ec234 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6383c83881908a978e471fe422a2 completed March 20, 2026, 3:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69be03b3b0208190bb307cdd53f44306 completed March 21, 2026, 2:34 a.m.
NEDg Description generation batch_69be0440e7c881908743b7af9b2fa347 completed March 21, 2026, 2:36 a.m.
NED2 Entity disambiguation (via description) batch_69be04e21df88190b98ed7b3e27b818c completed March 21, 2026, 2:39 a.m.
Created at: March 20, 2026, 1:16 p.m.