Triple

T1179504
Position Surface form Disambiguated ID Type / Status
Subject Rwanda E25102 entity
Predicate majorEthnicGroup P1898 FINISHED
Object Twa
The Twa are an indigenous pygmy people of Central Africa, traditionally forest-dwelling hunter-gatherers and one of the region’s oldest ethnic groups.
 E136911 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: Twa | Statement: [Rwanda, majorEthnicGroup, Twa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Twa
Context triple: [Rwanda, majorEthnicGroup, Twa]
  • A. Tuka
    Tuka is a surname most notably associated with Vojtech Tuka, a Slovak politician and leading figure of the World War II-era Slovak State.
  • B. Tuka
    Tuka is the affectionate self-referential name used by the 17th-century Marathi saint-poet Tukaram in his devotional abhangas.
  • C. Katwa
    Katwa is a health zone and town in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected during the 2018–2020 Kivu Ebola epidemic.
  • D. Wanetsi
    Wanetsi is a distinct and archaic variety of Pashto spoken by a small community in parts of Afghanistan and Pakistan.
  • E. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • 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: Twa
Triple: [Rwanda, majorEthnicGroup, Twa]
Generated description
The Twa are an indigenous pygmy people of Central Africa, traditionally forest-dwelling hunter-gatherers and one of the region’s oldest ethnic groups.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Twa
Target entity description: The Twa are an indigenous pygmy people of Central Africa, traditionally forest-dwelling hunter-gatherers and one of the region’s oldest ethnic groups.
  • A. Tuka
    Tuka is a surname most notably associated with Vojtech Tuka, a Slovak politician and leading figure of the World War II-era Slovak State.
  • B. Tuka
    Tuka is the affectionate self-referential name used by the 17th-century Marathi saint-poet Tukaram in his devotional abhangas.
  • C. Katwa
    Katwa is a health zone and town in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected during the 2018–2020 Kivu Ebola epidemic.
  • D. Wanetsi
    Wanetsi is a distinct and archaic variety of Pashto spoken by a small community in parts of Afghanistan and Pakistan.
  • E. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd1226fc819083d526ecd22af8ef completed March 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac764827b881908cd2bb1e11e179f3 completed March 7, 2026, 7:02 p.m.
NEDg Description generation batch_69ac77ba5cf08190a80a9e35f99aa7c3 completed March 7, 2026, 7:08 p.m.
NED2 Entity disambiguation (via description) batch_69ac781e4e5481909d56c790d46660ef completed March 7, 2026, 7:10 p.m.
Created at: March 1, 2026, 7:45 p.m.