Triple

T1316663
Position Surface form Disambiguated ID Type / Status
Subject Mandinka E28118 entity
Predicate hasAlternativeName P39 FINISHED
Object Mandika
Mandika is an alternative name for the Mandinka, a major West African ethnic group known for their rich cultural traditions and historical role in the Mali Empire.
 E150323 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: Mandika | Statement: [Mandinka, hasAlternativeName, Mandika]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mandika
Context triple: [Mandinka, hasAlternativeName, Mandika]
  • A. Mangina
    Mangina is a town in North Kivu Province in the eastern Democratic Republic of the Congo that gained international attention as a focal point of the 2018–2020 Kivu Ebola epidemic.
  • B. Kagizman
    Kagizman is a town in eastern Turkey, historically part of the former Kars Oblast in the Caucasus region.
  • C. Magindanawn
    Magindanawn is an Austronesian language spoken by the Maguindanaon people of Mindanao in the southern Philippines.
  • D. Negaraku
    Negaraku is the national anthem of Malaysia, symbolizing the country's sovereignty and unity.
  • E. Zakumi
    Zakumi is the leopard-themed mascot character created to represent South Africa and embody the spirit of the 2010 FIFA World Cup.
  • 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: Mandika
Triple: [Mandinka, hasAlternativeName, Mandika]
Generated description
Mandika is an alternative name for the Mandinka, a major West African ethnic group known for their rich cultural traditions and historical role in the Mali Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mandika
Target entity description: Mandika is an alternative name for the Mandinka, a major West African ethnic group known for their rich cultural traditions and historical role in the Mali Empire.
  • A. Mangina
    Mangina is a town in North Kivu Province in the eastern Democratic Republic of the Congo that gained international attention as a focal point of the 2018–2020 Kivu Ebola epidemic.
  • B. Kagizman
    Kagizman is a town in eastern Turkey, historically part of the former Kars Oblast in the Caucasus region.
  • C. Magindanawn
    Magindanawn is an Austronesian language spoken by the Maguindanaon people of Mindanao in the southern Philippines.
  • D. Negaraku
    Negaraku is the national anthem of Malaysia, symbolizing the country's sovereignty and unity.
  • E. Zakumi
    Zakumi is the leopard-themed mascot character created to represent South Africa and embody the spirit of the 2010 FIFA World Cup.
  • 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_69a498532c3481909223b74af2e578df completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c175079481909077cf11ed72d6fa completed March 1, 2026, 10:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69acbaf16a84819089c3473113ae70f9 completed March 7, 2026, 11:55 p.m.
NEDg Description generation batch_69acbb89269081909f00aee480c94e9f completed March 7, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_69acbc010cd0819080b1f8695dc0990b completed March 8, 2026, midnight
Created at: March 1, 2026, 7:55 p.m.