Triple

T7131594
Position Surface form Disambiguated ID Type / Status
Subject Mande E166201 entity
Predicate hasLanguage P15 FINISHED
Object Dyula
Dyula is a Mande language widely used as a trade and lingua franca in parts of West Africa, particularly in Burkina Faso, Côte d’Ivoire, and Mali.
 E643327 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: Dyula | Statement: [Mande, hasLanguage, Dyula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dyula
Context triple: [Mande, hasLanguage, Dyula]
  • A. Yassa
    Yassa was the codified legal and administrative code traditionally attributed to Genghis Khan that governed the Mongol Empire and its successor states.
  • B. Amidou
    Amidou is a character associated with sorcery and the mystical arts, often depicted in connection with a powerful sorcerer.
  • C. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • D. Makouda
    Makouda is a town and commune located in northern Algeria within the Kabylie region.
  • E. Mundemba
    Mundemba is a town in southwestern Cameroon known as a gateway to the biodiverse Korup National Park.
  • 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: Dyula
Triple: [Mande, hasLanguage, Dyula]
Generated description
Dyula is a Mande language widely used as a trade and lingua franca in parts of West Africa, particularly in Burkina Faso, Côte d’Ivoire, and Mali.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dyula
Target entity description: Dyula is a Mande language widely used as a trade and lingua franca in parts of West Africa, particularly in Burkina Faso, Côte d’Ivoire, and Mali.
  • A. Yassa
    Yassa was the codified legal and administrative code traditionally attributed to Genghis Khan that governed the Mongol Empire and its successor states.
  • B. Amidou
    Amidou is a character associated with sorcery and the mystical arts, often depicted in connection with a powerful sorcerer.
  • C. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • D. Makouda
    Makouda is a town and commune located in northern Algeria within the Kabylie region.
  • E. Mundemba
    Mundemba is a town in southwestern Cameroon known as a gateway to the biodiverse Korup National Park.
  • 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_69c68884a9388190af42f90d1c1a7151 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e66f15b88190bc1fb0f0a8af16a6 completed March 27, 2026, 8:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a33eea0481909f87e0813bc35b52 completed March 28, 2026, 9:45 a.m.
NEDg Description generation batch_69c7a3f2b51c81909f058149e9bd9f0a completed March 28, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69c7a4a9e91881909df07f1c540f191e completed March 28, 2026, 9:51 a.m.
Created at: March 27, 2026, 2:44 p.m.