Triple

T6700717
Position Surface form Disambiguated ID Type / Status
Subject Tswa language E152870 entity
Predicate hasDialect P4251 FINISHED
Object Dzivi
Dzivi is a dialect of the Tswa (Xitswa) Bantu language spoken in parts of southern Africa.
 E614291 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: Dzivi | Statement: [Tswa language, hasDialect, Dzivi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dzivi
Context triple: [Tswa language, hasDialect, Dzivi]
  • A. Kwaluudhi
    Kwaluudhi is a dialect of the Ovambo language spoken by a specific Ovambo subgroup in northern Namibia.
  • B. Ndungane
    Ndungane is a surname most notably associated with South African Anglican archbishop and social justice advocate Njongonkulu Ndungane.
  • C. Ndzebi
    Ndzebi is a Bantu language spoken primarily by the Nzebi people of Gabon and neighboring regions.
  • D. Zamdela
    Zamdela is a township suburb of Sasolburg in South Africa, primarily serving as a residential area for workers in the nearby industrial and petrochemical complexes.
  • E. Zalongo
    Zalongo is a historic village and archaeological area in Epirus, Greece, best known for the 19th-century mass suicide of Souliot women commemorated by the Dance of Zalongo.
  • 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: Dzivi
Triple: [Tswa language, hasDialect, Dzivi]
Generated description
Dzivi is a dialect of the Tswa (Xitswa) Bantu language spoken in parts of southern Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dzivi
Target entity description: Dzivi is a dialect of the Tswa (Xitswa) Bantu language spoken in parts of southern Africa.
  • A. Kwaluudhi
    Kwaluudhi is a dialect of the Ovambo language spoken by a specific Ovambo subgroup in northern Namibia.
  • B. Ndungane
    Ndungane is a surname most notably associated with South African Anglican archbishop and social justice advocate Njongonkulu Ndungane.
  • C. Ndzebi
    Ndzebi is a Bantu language spoken primarily by the Nzebi people of Gabon and neighboring regions.
  • D. Zamdela
    Zamdela is a township suburb of Sasolburg in South Africa, primarily serving as a residential area for workers in the nearby industrial and petrochemical complexes.
  • E. Zalongo
    Zalongo is a historic village and archaeological area in Epirus, Greece, best known for the 19th-century mass suicide of Souliot women commemorated by the Dance of Zalongo.
  • 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_69c68807adbc8190b8632df42b39eda0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d0e4a1848190997520ddd7808cc6 completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70081395c8190921636db5cfa096a completed March 27, 2026, 10:11 p.m.
NEDg Description generation batch_69c704f464f88190be8163b2dfd32bcf completed March 27, 2026, 10:30 p.m.
NED2 Entity disambiguation (via description) batch_69c705db3098819083ce9a93e429b758 completed March 27, 2026, 10:34 p.m.
Created at: March 27, 2026, 2:05 p.m.