Triple

T22686497
Position Surface form Disambiguated ID Type / Status
Subject Kasindi E560930 entity
Predicate roadConnectionTo P9041 FINISHED
Object Mpondwe
Mpondwe is a border town in western Uganda that serves as a major crossing and trade route between Uganda and the Democratic Republic of the Congo.
 E1559741 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: Mpondwe | Statement: [Kasindi, roadConnectionTo, Mpondwe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mpondwe
Context triple: [Kasindi, roadConnectionTo, Mpondwe]
  • A. Tsumkwe
    Tsumkwe is a remote settlement in northeastern Namibia known as a center of San (Bushmen) communities and culture.
  • B. Ilanga
    Ilanga is a South African newspaper, historically significant as one of the country’s oldest isiZulu-language publications.
  • C. Keabetswe
    Keabetswe is the given first name of Mokgweetsi Masisi, the president of Botswana.
  • D. Tembisa
    Tembisa is a large township in Gauteng, South Africa, situated on the East Rand and known as a densely populated residential area within the City of Ekurhuleni.
  • E. Gatenga
    Gatenga is an urban sector within Kigali, Rwanda, known for its residential neighborhoods and local commercial activity.
  • 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: Mpondwe
Triple: [Kasindi, roadConnectionTo, Mpondwe]
Generated description
Mpondwe is a border town in western Uganda that serves as a major crossing and trade route between Uganda and the Democratic Republic of the Congo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mpondwe
Target entity description: Mpondwe is a border town in western Uganda that serves as a major crossing and trade route between Uganda and the Democratic Republic of the Congo.
  • A. Tsumkwe
    Tsumkwe is a remote settlement in northeastern Namibia known as a center of San (Bushmen) communities and culture.
  • B. Ilanga
    Ilanga is a South African newspaper, historically significant as one of the country’s oldest isiZulu-language publications.
  • C. Keabetswe
    Keabetswe is the given first name of Mokgweetsi Masisi, the president of Botswana.
  • D. Tembisa
    Tembisa is a large township in Gauteng, South Africa, situated on the East Rand and known as a densely populated residential area within the City of Ekurhuleni.
  • E. Gatenga
    Gatenga is an urban sector within Kigali, Rwanda, known for its residential neighborhoods and local commercial activity.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178649aac8190a9d41f5d82895bdf completed April 29, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bb9aa45cc8190b71d985bd3c1d408 completed May 19, 2026, 1:15 a.m.
NEDg Description generation batch_6a0bbb38da508190bc1d9bc8538cdbe2 completed May 19, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_6a0bbc1bd0808190a0a5f8f603308b45 completed May 19, 2026, 1:25 a.m.
Created at: April 17, 2026, 3:12 p.m.