Triple

T14289099
Position Surface form Disambiguated ID Type / Status
Subject Aranuka E354260 entity
Predicate airportIATA P418 FINISHED
Object AAK
AAK is the IATA airport code for Aranuka Airport, which serves the island of Aranuka in Kiribati.
E1091944 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: AAK | Statement: [Aranuka, airportIATA, AAK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AAK
Context triple: [Aranuka, airportIATA, AAK]
  • A. AKK
    AKK is the IATA airport code for Akhiok Airport, a small public airport serving the community of Akhiok in Alaska, United States.
  • B. AA
    AA is the two-letter IATA airline designator used to identify American Airlines in flight schedules, tickets, and aviation systems.
  • C. AA
    AA is a UK welfare benefit that provides financial support to older people who need help with personal care due to illness or disability.
  • D. AA
    AA was the common abbreviation for the German Foreign Office (Auswärtiges Amt) during the Nazi era.
  • E. AA
    AA is a historic minor league professional baseball organization in the United States that has served as a key developmental league for Major League Baseball.
  • 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: AAK
Triple: [Aranuka, airportIATA, AAK]
Generated description
AAK is the IATA airport code for Aranuka Airport, which serves the island of Aranuka in Kiribati.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AAK
Target entity description: AAK is the IATA airport code for Aranuka Airport, which serves the island of Aranuka in Kiribati.
  • A. AKK
    AKK is the IATA airport code for Akhiok Airport, a small public airport serving the community of Akhiok in Alaska, United States.
  • B. AA
    AA is the two-letter IATA airline designator used to identify American Airlines in flight schedules, tickets, and aviation systems.
  • C. AA
    AA is a UK welfare benefit that provides financial support to older people who need help with personal care due to illness or disability.
  • D. AA
    AA is the vehicle registration code used on license plates to identify motor vehicles registered in the town of Aalen, Germany.
  • E. AA
    AA was the common abbreviation for the German Foreign Office (Auswärtiges Amt) during the Nazi era.
  • 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_69d8278e17088190b328c5a9d4be74ff completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de698023288190b1d705235c2b2ca3 completed April 14, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d1e14d4819091c381f96c43c58b completed May 8, 2026, 1:32 a.m.
NEDg Description generation batch_69fd3e6dde6081908a37817e4dd22ecd completed May 8, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69fd3f42ccdc81908399d8f9a2f0da31 completed May 8, 2026, 1:41 a.m.
Created at: April 10, 2026, 1:11 a.m.