Triple

T21665087
Position Surface form Disambiguated ID Type / Status
Subject Southern Malawi E534692 entity
Predicate hasMajorCity P316 FINISHED
Object Mangochi
Mangochi is a lakeside town in southern Malawi known as a major commercial and tourist center near the southern end of Lake Malawi.
 E1495208 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: Mangochi | Statement: [Southern Malawi, hasMajorCity, Mangochi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mangochi
Context triple: [Southern Malawi, hasMajorCity, Mangochi]
  • A. Mungaka
    Mungaka is a Grassfields Bantu language spoken primarily in Cameroon, particularly associated with the Bamunka (Ndop) area.
  • B. Oshikwambi
    Oshikwambi is a regional dialect of the Oshiwambo language spoken by the Kwambi people in northern Namibia.
  • C. Mwenga
    Mwenga is a town in the South Kivu province of the Democratic Republic of the Congo that serves as an administrative and commercial center for the surrounding region.
  • D. Mangini
    Mangini is an Italian surname most notably associated with former NFL head coach and analyst Eric Mangini.
  • E. Yumbe
    Yumbe is a town in northern Uganda that serves as an important local administrative and commercial center near the border with South Sudan.
  • 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: Mangochi
Triple: [Southern Malawi, hasMajorCity, Mangochi]
Generated description
Mangochi is a lakeside town in southern Malawi known as a major commercial and tourist center near the southern end of Lake Malawi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mangochi
Target entity description: Mangochi is a lakeside town in southern Malawi known as a major commercial and tourist center near the southern end of Lake Malawi.
  • A. Mungaka
    Mungaka is a Grassfields Bantu language spoken primarily in Cameroon, particularly associated with the Bamunka (Ndop) area.
  • B. Oshikwambi
    Oshikwambi is a regional dialect of the Oshiwambo language spoken by the Kwambi people in northern Namibia.
  • C. Mwenga
    Mwenga is a town in the South Kivu province of the Democratic Republic of the Congo that serves as an administrative and commercial center for the surrounding region.
  • D. Mangini
    Mangini is an Italian surname most notably associated with former NFL head coach and analyst Eric Mangini.
  • E. Yumbe
    Yumbe is a town in northern Uganda that serves as an important local administrative and commercial center near the border with South Sudan.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c0b26c8819092c13e59dcc3c25c completed April 27, 2026, 2 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a15a0fcb8819095a7ada7e746a1ef completed May 17, 2026, 7:23 p.m.
NEDg Description generation batch_6a0a165552f48190aab079b317c6e281 completed May 17, 2026, 7:26 p.m.
NED2 Entity disambiguation (via description) batch_6a0a1704fb4c819086a689ccced74f90 completed May 17, 2026, 7:29 p.m.
Created at: April 16, 2026, 6:36 p.m.