Triple

T1583848
Position Surface form Disambiguated ID Type / Status
Subject Kigoma E34026 entity
Predicate connectedByFerryTo P1831 FINISHED
Object Bujumbura
Bujumbura is the largest city and former capital of Burundi, located on the northeastern shore of Lake Tanganyika.
 E26895 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: Bujumbura | Statement: [Kigoma, connectedByFerryTo, Bujumbura]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bujumbura
Context triple: [Kigoma, connectedByFerryTo, Bujumbura]
  • A. Kigali
    Kigali is the capital and largest city of Rwanda, known as a major political and economic hub in East Africa.
  • B. Africa/Bujumbura
    Africa/Bujumbura is the IANA time zone identifier representing the local time observed in Bujumbura, Burundi, which follows Central Africa Time.
  • C. Masvingo
    Masvingo is one of Zimbabwe’s oldest urban centers, located in the country’s southeastern region near the Great Zimbabwe ruins.
  • D. Kisangani
    Kisangani is a major city in northeastern Democratic Republic of the Congo, known as a key inland port and commercial center in the central African rainforest region.
  • E. Gwanda
    Gwanda is a small Zimbabwean town that serves as an administrative and commercial hub in the country’s arid south, known historically for cattle ranching and gold mining.
  • 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: Bujumbura
Triple: [Kigoma, connectedByFerryTo, Bujumbura]
Generated description
Bujumbura is the largest city and former capital of Burundi, located on the northeastern shore of Lake Tanganyika.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bujumbura
Target entity description: Bujumbura is the largest city and former capital of Burundi, located on the northeastern shore of Lake Tanganyika.
  • A. Kigali
    Kigali is the capital and largest city of Rwanda, known as a major political and economic hub in East Africa.
  • B. Africa/Bujumbura chosen
    Africa/Bujumbura is the IANA time zone identifier representing the local time observed in Bujumbura, Burundi, which follows Central Africa Time.
  • C. Masvingo
    Masvingo is one of Zimbabwe’s oldest urban centers, located in the country’s southeastern region near the Great Zimbabwe ruins.
  • D. Kisangani
    Kisangani is a major city in northeastern Democratic Republic of the Congo, known as a key inland port and commercial center in the central African rainforest region.
  • E. Gwanda
    Gwanda is a small Zimbabwean town that serves as an administrative and commercial hub in the country’s arid south, known historically for cattle ranching and gold mining.
  • F. None of above.

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_69a885fceb2c8190b47e0f7c0aefbff0 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908f0e72c8190bb7a2a0c77379060 completed March 5, 2026, 4:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4035dd7c8190817301c0a2b0b938 completed March 8, 2026, 9:24 a.m.
NEDg Description generation batch_69ad411829fc81909f9dc88b3d55d431 completed March 8, 2026, 9:27 a.m.
NED2 Entity disambiguation (via description) batch_69ad417fa778819092ebabad8bdcddd3 completed March 8, 2026, 9:29 a.m.
Created at: March 4, 2026, 7:27 p.m.