Triple

T6683867
Position Surface form Disambiguated ID Type / Status
Subject Miriam Makeba E152051 entity
Predicate notableAlbum P4 FINISHED
Object Sangoma
Sangoma is a 1988 album by South African singer and activist Miriam Makeba that draws heavily on traditional African songs and spiritual themes.
 E612074 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: Sangoma | Statement: [Miriam Makeba, notableAlbum, Sangoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sangoma
Context triple: [Miriam Makeba, notableAlbum, Sangoma]
  • A. Xola
    Xola is a Mexico City Metro station on Line 2 that serves the southern part of the city near the Calzada de Tlalpan corridor.
  • B. Gonja
    Gonja are an ethnic group in northern Ghana known for their distinct language, chieftaincy traditions, and historical Gonja kingdom.
  • C. Soshanguve
    Soshanguve is a large township in the northern part of the Gauteng province of South Africa, known for its diverse population and proximity to Pretoria.
  • D. Chambeali
    Chambeali is an Indo-Aryan language spoken primarily in the Chamba region of Himachal Pradesh in northern India.
  • E. Ngamo
    Ngamo is a West Chadic language spoken primarily in northeastern Nigeria by the Ngamo 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: Sangoma
Triple: [Miriam Makeba, notableAlbum, Sangoma]
Generated description
Sangoma is a 1988 album by South African singer and activist Miriam Makeba that draws heavily on traditional African songs and spiritual themes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sangoma
Target entity description: Sangoma is a 1988 album by South African singer and activist Miriam Makeba that draws heavily on traditional African songs and spiritual themes.
  • A. Xola
    Xola is a Mexico City Metro station on Line 2 that serves the southern part of the city near the Calzada de Tlalpan corridor.
  • B. Gonja
    Gonja are an ethnic group in northern Ghana known for their distinct language, chieftaincy traditions, and historical Gonja kingdom.
  • C. Soshanguve
    Soshanguve is a large township in the northern part of the Gauteng province of South Africa, known for its diverse population and proximity to Pretoria.
  • D. Chambeali
    Chambeali is an Indo-Aryan language spoken primarily in the Chamba region of Himachal Pradesh in northern India.
  • E. Ngamo
    Ngamo is a West Chadic language spoken primarily in northeastern Nigeria by the Ngamo 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_69c687f9977c819097e7f5ada4fe522e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b122df14819082068af37611b691 completed March 27, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7ae8f388190a3c78c89b7293804 completed March 27, 2026, 9:33 p.m.
NEDg Description generation batch_69c6f9f7b4b08190b5c4dab67758af67 completed March 27, 2026, 9:43 p.m.
NED2 Entity disambiguation (via description) batch_69c6fac7c0e881909b4c2058beebda9f completed March 27, 2026, 9:46 p.m.
Created at: March 27, 2026, 2:04 p.m.