Triple

T6771983
Position Surface form Disambiguated ID Type / Status
Subject Twi E155064 entity
Predicate hasDialect P4251 FINISHED
Object Akyem Twi
Akyem Twi is a regional variety of the Akan language spoken primarily by the Akyem people in Ghana.
 E620971 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: Akyem Twi | Statement: [Twi, hasDialect, Akyem Twi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Akyem Twi
Context triple: [Twi, hasDialect, Akyem Twi]
  • A. Akuapem Twi
    Akuapem Twi is a major dialect of the Akan language spoken primarily in the Akuapem area of Ghana and widely used in education, media, and religious contexts.
  • B. Asante Twi
    Asante Twi is a major dialect of the Akan language spoken predominantly by the Asante people in Ghana and widely used in education, media, and everyday communication.
  • C. Akpafu dialect
    The Akpafu dialect is a regional variety of the Siwu language spoken by the Akpafu people in the Volta Region of Ghana.
  • D. Fante language
    Fante language is a major dialect of the Akan language spoken primarily by the Fante people in coastal Ghana.
  • E. Ewe
    Ewe is a major Niger–Congo language spoken primarily in southeastern Ghana and southern Togo by the Ewe people.
  • 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: Akyem Twi
Triple: [Twi, hasDialect, Akyem Twi]
Generated description
Akyem Twi is a regional variety of the Akan language spoken primarily by the Akyem people in Ghana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Akyem Twi
Target entity description: Akyem Twi is a regional variety of the Akan language spoken primarily by the Akyem people in Ghana.
  • A. Akuapem Twi
    Akuapem Twi is a major dialect of the Akan language spoken primarily in the Akuapem area of Ghana and widely used in education, media, and religious contexts.
  • B. Asante Twi
    Asante Twi is a major dialect of the Akan language spoken predominantly by the Asante people in Ghana and widely used in education, media, and everyday communication.
  • C. Akpafu dialect
    The Akpafu dialect is a regional variety of the Siwu language spoken by the Akpafu people in the Volta Region of Ghana.
  • D. Fante language
    Fante language is a major dialect of the Akan language spoken primarily by the Fante people in coastal Ghana.
  • E. Ewe
    Ewe is a major Niger–Congo language spoken primarily in southeastern Ghana and southern Togo by the Ewe people.
  • 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_69c68812ef7c819099369f51febb725c completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d24aaf948190a544cc28b7de67c4 completed March 27, 2026, 6:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723c67dc08190b21138488c80733a completed March 28, 2026, 12:41 a.m.
NEDg Description generation batch_69c724691b8081908975aec09e25dec2 completed March 28, 2026, 12:44 a.m.
NED2 Entity disambiguation (via description) batch_69c724bbe8f88190b2abe734b267aea7 completed March 28, 2026, 12:45 a.m.
Created at: March 27, 2026, 2:13 p.m.