Triple

T4528975
Position Surface form Disambiguated ID Type / Status
Subject Inverness Airport E106247 entity
Predicate IATAcode P418 FINISHED
Object INV
INV is the three-letter IATA airport code for Inverness Airport in the Scottish Highlands.
 E449312 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: INV | Statement: [Inverness Airport, IATAcode, INV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: INV
Context triple: [Inverness Airport, IATAcode, INV]
  • A. INST
    INST is the stock ticker symbol for Instructure, an education technology company best known for its Canvas learning management system.
  • B. INS
    INS was the former U.S. federal agency responsible for administering and enforcing immigration and naturalization laws before its functions were transferred to the Department of Homeland Security.
  • C. Ins
    Ins is a small Swiss municipality located in the Seeland region of the canton of Bern, known for its agricultural landscape and proximity to the lakes of Biel, Neuchâtel, and Murten.
  • D. IN
    IN is the two-letter ISO 3166-1 alpha-2 country code representing India in international standards and systems.
  • E. IN
    IN is the official two-letter United States Postal Service abbreviation for the state of Indiana.
  • 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: INV
Triple: [Inverness Airport, IATAcode, INV]
Generated description
INV is the three-letter IATA airport code for Inverness Airport in the Scottish Highlands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: INV
Target entity description: INV is the three-letter IATA airport code for Inverness Airport in the Scottish Highlands.
  • A. INST
    INST is the stock ticker symbol for Instructure, an education technology company best known for its Canvas learning management system.
  • B. INS
    INS was the former U.S. federal agency responsible for administering and enforcing immigration and naturalization laws before its functions were transferred to the Department of Homeland Security.
  • C. Ins
    Ins is a small Swiss municipality located in the Seeland region of the canton of Bern, known for its agricultural landscape and proximity to the lakes of Biel, Neuchâtel, and Murten.
  • D. IN
    IN is the official two-letter United States Postal Service abbreviation for the state of Indiana.
  • E. IN
    IN is the two-letter ISO 3166-1 alpha-2 country code representing India in international standards and systems.
  • 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_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd5779593081908593537b9239e01b completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bda45eadd0819093429e14c88a161d completed March 20, 2026, 7:47 p.m.
NEDg Description generation batch_69bda4e4f5a081908892c4363b3a4989 completed March 20, 2026, 7:49 p.m.
NED2 Entity disambiguation (via description) batch_69bda556d4188190a00d6e6259139c10 completed March 20, 2026, 7:51 p.m.
Created at: March 20, 2026, 1:03 p.m.