Triple

T15245708
Position Surface form Disambiguated ID Type / Status
Subject Bambara people E364373 entity
Predicate historicalCapital P2536 FINISHED
Object Kaarta
Kaarta was a precolonial West African kingdom that served as a major political and cultural center for the Bambara people in what is now Mali.
 E1145591 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: Kaarta | Statement: [Bambara people, historicalCapital, Kaarta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kaarta
Context triple: [Bambara people, historicalCapital, Kaarta]
  • A. Kasoa
    Kasoa is a rapidly growing urban town in southern Ghana that serves as a major residential and commercial hub on the outskirts of Accra.
  • B. Moru
    Moru is a Central Sudanic language spoken primarily by the Moru people in South Sudan.
  • C. Kutaisi
    Kutaisi is one of Georgia’s major cities, historically significant and formerly a capital, located in the western part of the country.
  • D. Makkena
    Makkena is the surname of American actress Wendy Makkena, known for her roles in films such as "Sister Act" and various television series.
  • E. Hatta
    Hatta is an Indonesian surname most prominently associated with Mohammad Hatta, the country’s first vice president and a leading figure in the struggle for independence.
  • 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: Kaarta
Triple: [Bambara people, historicalCapital, Kaarta]
Generated description
Kaarta was a precolonial West African kingdom that served as a major political and cultural center for the Bambara people in what is now Mali.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kaarta
Target entity description: Kaarta was a precolonial West African kingdom that served as a major political and cultural center for the Bambara people in what is now Mali.
  • A. Kasoa
    Kasoa is a rapidly growing urban town in southern Ghana that serves as a major residential and commercial hub on the outskirts of Accra.
  • B. Moru
    Moru is a Central Sudanic language spoken primarily by the Moru people in South Sudan.
  • C. Kutaisi
    Kutaisi is one of Georgia’s major cities, historically significant and formerly a capital, located in the western part of the country.
  • D. Makkena
    Makkena is the surname of American actress Wendy Makkena, known for her roles in films such as "Sister Act" and various television series.
  • E. Hatta
    Hatta is an Indonesian surname most prominently associated with Mohammad Hatta, the country’s first vice president and a leading figure in the struggle for independence.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007f306f08190be448b215d6c9b6c completed April 15, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd461cf08190a506aac2f0cec83a completed May 9, 2026, 7:07 a.m.
NEDg Description generation batch_69fedf6ee3f081909553078cd3e9d243 completed May 9, 2026, 7:17 a.m.
NED2 Entity disambiguation (via description) batch_69fee0016a088190ad87268e035f677e completed May 9, 2026, 7:19 a.m.
Created at: April 10, 2026, 3:13 a.m.