Triple

T6771391
Position Surface form Disambiguated ID Type / Status
Subject Dangme language E155049 entity
Predicate subfamily P4180 FINISHED
Object Kwa
Kwa is a major branch of the Niger-Congo language family that encompasses numerous languages spoken primarily in southern Ghana, Côte d’Ivoire, Togo, and neighboring West African countries.
 E617321 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: Kwa | Statement: [Dangme language, subfamily, Kwa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kwa
Context triple: [Dangme language, subfamily, Kwa]
  • A. Waase
    Waase is a small village on the island of Ummanz in the German state of Mecklenburg-Vorpommern.
  • B. Kuje
    Kuje is a town and local government area located within Nigeria’s Federal Capital Territory, near the capital city of Abuja.
  • C. Wala
    The Wala are an ethnic group primarily inhabiting the Upper West Region of Ghana, known for their Islamic heritage, centralized chieftaincy system, and rich traditions in trade and craftsmanship.
  • D. Wala
    Wala is an Oceanic language variety spoken in Vanuatu, recognized as one of the dialects within the Uripiv-Wala-Rano-Atchin dialect chain.
  • E. Washo
    Washo is a Native American language isolate traditionally spoken by the Washoe people of the Lake Tahoe region in California and Nevada.
  • 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: Kwa
Triple: [Dangme language, subfamily, Kwa]
Generated description
Kwa is a major branch of the Niger-Congo language family that encompasses numerous languages spoken primarily in southern Ghana, Côte d’Ivoire, Togo, and neighboring West African countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kwa
Target entity description: Kwa is a major branch of the Niger-Congo language family that encompasses numerous languages spoken primarily in southern Ghana, Côte d’Ivoire, Togo, and neighboring West African countries.
  • A. Waase
    Waase is a small village on the island of Ummanz in the German state of Mecklenburg-Vorpommern.
  • B. Kuje
    Kuje is a town and local government area located within Nigeria’s Federal Capital Territory, near the capital city of Abuja.
  • C. Wala
    The Wala are an ethnic group primarily inhabiting the Upper West Region of Ghana, known for their Islamic heritage, centralized chieftaincy system, and rich traditions in trade and craftsmanship.
  • D. Wala
    Wala is an Oceanic language variety spoken in Vanuatu, recognized as one of the dialects within the Uripiv-Wala-Rano-Atchin dialect chain.
  • E. Washo
    Washo is a Native American language isolate traditionally spoken by the Washoe people of the Lake Tahoe region in California and Nevada.
  • 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_69c6d2496fa08190895d8b625fb0d699 completed March 27, 2026, 6:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c712c46b70819097401afab991c808 completed March 27, 2026, 11:29 p.m.
NEDg Description generation batch_69c713853bf88190a8a07fd9f4ea1687 completed March 27, 2026, 11:32 p.m.
NED2 Entity disambiguation (via description) batch_69c713ead2a48190bbf95caf2ca8d997 completed March 27, 2026, 11:34 p.m.
Created at: March 27, 2026, 2:13 p.m.