Triple

T17345650
Position Surface form Disambiguated ID Type / Status
Subject Mount Isa Airport E421680 entity
Predicate IATACode P418 FINISHED
Object ISA
ISA is the IATA airport code for Mount Isa Airport in Queensland, Australia.
 E423658 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: ISA | Statement: [Mount Isa Airport, IATACode, ISA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ISA
Context triple: [Mount Isa Airport, IATACode, ISA]
  • A. ISA
    ISA (Industry Standard Architecture) is an early computer bus standard used in IBM PCs and compatible systems to connect expansion cards and peripherals to the motherboard.
  • B. ISA
    ISA is the acronym for the International Seabed Authority, the intergovernmental organization responsible for regulating mineral-related activities in the international seabed area beyond national jurisdiction.
  • C. ISA
    ISA is the commonly used abbreviation for the Israel State Archives, the national repository for Israeli government records and historical documents.
  • D. ISA
    ISA is the commonly used abbreviation for Integrated Science Assessments, which are comprehensive evaluations of scientific data used to inform environmental and regulatory decisions.
  • E. ISA
    ISA is the abbreviated name of Japan’s Immigration Services Agency, the government body responsible for immigration control and residency management.
  • 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: ISA
Triple: [Mount Isa Airport, IATACode, ISA]
Generated description
ISA is the IATA airport code for Mount Isa Airport in Queensland, Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ISA
Target entity description: ISA is the IATA airport code for Mount Isa Airport in Queensland, Australia.
  • A. ISA chosen
    ISA is the IATA airport code for Mount Isa Airport, a regional airport serving the mining city of Mount Isa in Queensland, Australia.
  • B. ISA
    ISA is the acronym for the International Seabed Authority, the intergovernmental organization responsible for regulating mineral-related activities in the international seabed area beyond national jurisdiction.
  • C. ISA
    ISA is the abbreviated name of Japan’s Immigration Services Agency, the government body responsible for immigration control and residency management.
  • D. ISA
    ISA is the commonly used abbreviation for Integrated Science Assessments, which are comprehensive evaluations of scientific data used to inform environmental and regulatory decisions.
  • E. ISA
    ISA is the commonly used abbreviation for the Israel State Archives, the national repository for Israeli government records and historical documents.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a286d34819080c5148c220fd5a1 completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a018c5be49c8190b27a4fe1df8e8ab6 completed May 11, 2026, 7:59 a.m.
NEDg Description generation batch_6a018ce8c6b481909c6c1a82364cbd90 completed May 11, 2026, 8:01 a.m.
NED2 Entity disambiguation (via description) batch_6a018d7ad50881908f80152db524f0af completed May 11, 2026, 8:04 a.m.
Created at: April 10, 2026, 5:44 a.m.