Triple

T2446311
Position Surface form Disambiguated ID Type / Status
Subject Ewe E53601 entity
Predicate standardVariety P751 FINISHED
Object Amedzofe dialect
The Amedzofe dialect is a regional variety of the Ewe language spoken in and around the town of Amedzofe in Ghana.
 E267650 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: Amedzofe dialect | Statement: [Ewe, standardVariety, Amedzofe dialect]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Amedzofe dialect
Context triple: [Ewe, standardVariety, Amedzofe dialect]
  • A. Ngeno-Ngene dialect
    The Ngeno-Ngene dialect is a regional variety of the Sasak language spoken on the island of Lombok in Indonesia, distinguished by its own phonological and lexical features.
  • B. Teke–Mbede languages
    The Teke–Mbede languages are a group of closely related Bantu languages spoken primarily in Gabon and neighboring Central African countries.
  • C. Bajelani dialect
    The Bajelani dialect is a regional variety of the Gorani language spoken by Kurdish communities in parts of the Middle East.
  • D. Banda-Ndélé language
    The Banda-Ndélé language is a Central Sudanic language spoken by the Banda people, primarily in the Central African Republic.
  • E. Baoulé language
    The Baoulé language is a Niger-Congo language spoken primarily by the Baoulé people of central Côte d'Ivoire.
  • 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: Amedzofe dialect
Triple: [Ewe, standardVariety, Amedzofe dialect]
Generated description
The Amedzofe dialect is a regional variety of the Ewe language spoken in and around the town of Amedzofe in Ghana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Amedzofe dialect
Target entity description: The Amedzofe dialect is a regional variety of the Ewe language spoken in and around the town of Amedzofe in Ghana.
  • A. Ngeno-Ngene dialect
    The Ngeno-Ngene dialect is a regional variety of the Sasak language spoken on the island of Lombok in Indonesia, distinguished by its own phonological and lexical features.
  • B. Teke–Mbede languages
    The Teke–Mbede languages are a group of closely related Bantu languages spoken primarily in Gabon and neighboring Central African countries.
  • C. Bajelani dialect
    The Bajelani dialect is a regional variety of the Gorani language spoken by Kurdish communities in parts of the Middle East.
  • D. Banda-Ndélé language
    The Banda-Ndélé language is a Central Sudanic language spoken by the Banda people, primarily in the Central African Republic.
  • E. Baoulé language
    The Baoulé language is a Niger-Congo language spoken primarily by the Baoulé people of central Côte d'Ivoire.
  • 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_69ab495d227c8190b26ae6548eeb1019 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abca25a84c8190859bf51000beffec completed March 7, 2026, 6:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0bd7a088190b635a8bac233c5cd completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef50bc7ac8190add8ee63c5621dc1 completed March 9, 2026, 4:27 p.m.
NED2 Entity disambiguation (via description) batch_69aef632e2e08190b21023cbb0f12be8 completed March 9, 2026, 4:32 p.m.
Created at: March 6, 2026, 9:43 p.m.