Triple

T220597
Position Surface form Disambiguated ID Type / Status
Subject Akademi Kreyòl Ayisyen E4203 entity
Predicate abbreviation P43 FINISHED
Object AKA
AKA is the standard abbreviation for Akademi Kreyòl Ayisyen, the official institution responsible for regulating and promoting the Haitian Creole language.
 E28120 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: AKA | Statement: [Akademi Kreyòl Ayisyen, abbreviation, AKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AKA
Context triple: [Akademi Kreyòl Ayisyen, abbreviation, AKA]
  • A. Anif
    Anif is a small Austrian municipality near Salzburg, known for its historic castle and as a residence of notable figures.
  • B. Aimaqs
    The Aimaqs are a collection of semi-nomadic, Persian-speaking ethnic groups primarily inhabiting western and central Afghanistan.
  • C. Kali
    Kali is a fierce and powerful Hindu goddess associated with time, destruction, and the transformative power that annihilates evil.
  • D. Alben
    Alben is a masculine given name most notably borne by Alben W. Barkley, the 35th vice president of the United States under President Harry S. Truman.
  • E. Kato
    Kato is the nickname of Kato Svanidze, who was the first wife of Soviet leader Joseph Stalin.
  • 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: AKA
Triple: [Akademi Kreyòl Ayisyen, abbreviation, AKA]
Generated description
AKA is the standard abbreviation for Akademi Kreyòl Ayisyen, the official institution responsible for regulating and promoting the Haitian Creole language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AKA
Target entity description: AKA is the standard abbreviation for Akademi Kreyòl Ayisyen, the official institution responsible for regulating and promoting the Haitian Creole language.
  • A. Anif
    Anif is a small Austrian municipality near Salzburg, known for its historic castle and as a residence of notable figures.
  • B. Aimaqs
    The Aimaqs are a collection of semi-nomadic, Persian-speaking ethnic groups primarily inhabiting western and central Afghanistan.
  • C. Kali
    Kali is a fierce and powerful Hindu goddess associated with time, destruction, and the transformative power that annihilates evil.
  • D. Alben
    Alben is a masculine given name most notably borne by Alben W. Barkley, the 35th vice president of the United States under President Harry S. Truman.
  • E. Kato
    Kato is the nickname of Kato Svanidze, who was the first wife of Soviet leader Joseph Stalin.
  • 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_69a2573508588190b522c2476d91acfe completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c6d0fa08190810139b14f4851bc completed Feb. 28, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3476fe7a0819086ce5c028429b2c0 completed Feb. 28, 2026, 7:52 p.m.
NEDg Description generation batch_69a34a3ad4688190acdcca286cd8a19a completed Feb. 28, 2026, 8:04 p.m.
NED2 Entity disambiguation (via description) batch_69a34a97c5dc8190b0f3e4f3c342cfae completed Feb. 28, 2026, 8:05 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.