Triple

T8498979
Position Surface form Disambiguated ID Type / Status
Subject Kayes E201167 entity
Predicate languageSpoken P151 FINISHED
Object Soninké
Soninké is a Mande language spoken primarily by the Soninké people across parts of Mali, Senegal, Mauritania, and neighboring West African countries.
 E740011 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: Soninké | Statement: [Kayes, languageSpoken, Soninké]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Soninké
Context triple: [Kayes, languageSpoken, Soninké]
  • A. Kissoué
    Kissoué is a town in southwestern Syria that gained historical significance as the site of a notable World War II battle during the Syria–Lebanon campaign.
  • B. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • C. 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.
  • D. Sissala
    Sissala are an ethnic group of northwestern Ghana, known for their distinct Gur language, agrarian lifestyle, and rich musical and oral traditions.
  • E. Zinza
    The Zinza are an ethnic group primarily inhabiting areas around Lake Victoria in northwestern Tanzania, known for their Bantu language and fishing and farming traditions.
  • 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: Soninké
Triple: [Kayes, languageSpoken, Soninké]
Generated description
Soninké is a Mande language spoken primarily by the Soninké people across parts of Mali, Senegal, Mauritania, and neighboring West African countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Soninké
Target entity description: Soninké is a Mande language spoken primarily by the Soninké people across parts of Mali, Senegal, Mauritania, and neighboring West African countries.
  • A. Kissoué
    Kissoué is a town in southwestern Syria that gained historical significance as the site of a notable World War II battle during the Syria–Lebanon campaign.
  • B. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • C. 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.
  • D. Sissala
    Sissala are an ethnic group of northwestern Ghana, known for their distinct Gur language, agrarian lifestyle, and rich musical and oral traditions.
  • E. Zinza
    The Zinza are an ethnic group primarily inhabiting areas around Lake Victoria in northwestern Tanzania, known for their Bantu language and fishing and farming traditions.
  • 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_69ca831ee390819095fae73400bbfafc completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5984d7481908c41c57bef9cf254 completed March 31, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4e0aa7788190abd7bb259966bc44 completed April 2, 2026, 11:07 a.m.
NEDg Description generation batch_69ce4ff668d4819081f4c3186437291b completed April 2, 2026, 11:16 a.m.
NED2 Entity disambiguation (via description) batch_69ce54cc52cc81908ca48c93956ca86e completed April 2, 2026, 11:36 a.m.
Created at: March 30, 2026, 6:14 p.m.