Triple

T3484776
Position Surface form Disambiguated ID Type / Status
Subject Adelaide Airport E73580 entity
Predicate IATAcode P418 FINISHED
Object ADL
ADL is the three-letter IATA airport code for Adelaide Airport, the main international and domestic airport serving Adelaide, South Australia.
 E360301 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: ADL | Statement: [Adelaide Airport, IATAcode, ADL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ADL
Context triple: [Adelaide Airport, IATAcode, ADL]
  • A. AAL
    AAL is the ICAO airline designator used in aviation to identify American Airlines in flight operations and air traffic control.
  • B. ALP
    ALP is the commonly used abbreviation for Bolivia’s Plurinational Legislative Assembly, the country’s national bicameral legislature.
  • C. ARL
    ARL (Australian Rugby League) was the top-level rugby league competition in Australia during the mid-1990s, preceding the formation of the National Rugby League (NRL).
  • D. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • E. ADUG
    ADUG is a private investment and development company based in Abu Dhabi, best known globally as the ownership group behind Manchester City Football Club.
  • 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: ADL
Triple: [Adelaide Airport, IATAcode, ADL]
Generated description
ADL is the three-letter IATA airport code for Adelaide Airport, the main international and domestic airport serving Adelaide, South Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ADL
Target entity description: ADL is the three-letter IATA airport code for Adelaide Airport, the main international and domestic airport serving Adelaide, South Australia.
  • A. AAL
    AAL is the ICAO airline designator used in aviation to identify American Airlines in flight operations and air traffic control.
  • B. ALP
    ALP is the commonly used abbreviation for Bolivia’s Plurinational Legislative Assembly, the country’s national bicameral legislature.
  • C. ARL
    ARL (Australian Rugby League) was the top-level rugby league competition in Australia during the mid-1990s, preceding the formation of the National Rugby League (NRL).
  • D. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • E. ADUG
    ADUG is a private investment and development company based in Abu Dhabi, best known globally as the ownership group behind Manchester City Football Club.
  • 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_69ad85b3c9b08190857cae74c7f36da9 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adbb795db88190805b26d9774fdb73 completed March 8, 2026, 6:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69b36820c90c819091b68cff7a0a2cda completed March 13, 2026, 1:28 a.m.
NEDg Description generation batch_69b3687bb5148190b73fd365383c4a89 completed March 13, 2026, 1:29 a.m.
NED2 Entity disambiguation (via description) batch_69b368ea71d081908332595324d8f873 completed March 13, 2026, 1:31 a.m.
Created at: March 8, 2026, 3:17 p.m.