Triple

T249682
Position Surface form Disambiguated ID Type / Status
Subject Kigoma Region E5115 entity
Predicate hasTown P847 FINISHED
Object Kasulu
Kasulu is a town in western Tanzania that serves as one of the main urban and commercial centers of the Kigoma Region.
 E35818 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: Kasulu | Statement: [Kigoma Region, hasTown, Kasulu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kasulu
Context triple: [Kigoma Region, hasTown, Kasulu]
  • A. Olosega
    Olosega is a small volcanic island in the Manuʻa group of American Samoa, known for its dramatic cliffs, lush vegetation, and connection by bridge to the neighboring island of Ofu.
  • B. Motsepe
    Motsepe is a prominent South African surname most notably associated with billionaire mining magnate and philanthropist Patrice Motsepe.
  • C. Terevaka
    Terevaka is a large extinct volcanic peak that forms the highest and youngest of the three main volcanoes making up Easter Island.
  • D. Zambezi Valley
    The Zambezi Valley is a vast, wildlife-rich river valley in southern Africa, known for its dramatic landscapes along the Zambezi River and protected areas such as Mana Pools.
  • E. Kiunguja
    Kiunguja is the Zanzibar-based variety of Swahili that historically served as the primary basis for the standardized form of the language.
  • 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: Kasulu
Triple: [Kigoma Region, hasTown, Kasulu]
Generated description
Kasulu is a town in western Tanzania that serves as one of the main urban and commercial centers of the Kigoma Region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kasulu
Target entity description: Kasulu is a town in western Tanzania that serves as one of the main urban and commercial centers of the Kigoma Region.
  • A. Olosega
    Olosega is a small volcanic island in the Manuʻa group of American Samoa, known for its dramatic cliffs, lush vegetation, and connection by bridge to the neighboring island of Ofu.
  • B. Motsepe
    Motsepe is a prominent South African surname most notably associated with billionaire mining magnate and philanthropist Patrice Motsepe.
  • C. Terevaka
    Terevaka is a large extinct volcanic peak that forms the highest and youngest of the three main volcanoes making up Easter Island.
  • D. Zambezi Valley
    The Zambezi Valley is a vast, wildlife-rich river valley in southern Africa, known for its dramatic landscapes along the Zambezi River and protected areas such as Mana Pools.
  • E. Kiunguja
    Kiunguja is the Zanzibar-based variety of Swahili that historically served as the primary basis for the standardized form of the language.
  • 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_69a257c4bf688190a46ebbf411ab7473 completed Feb. 28, 2026, 2:49 a.m.
NER Named-entity recognition batch_69a25d3728f0819086214ccc2db2305a completed Feb. 28, 2026, 3:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3914b6cb08190ae5413f46aedc23f completed March 1, 2026, 1:07 a.m.
NEDg Description generation batch_69a391b2c8088190bbbdf1f29c13f826 completed March 1, 2026, 1:09 a.m.
NED2 Entity disambiguation (via description) batch_69a39217ae2c819082fef73a105edf7d completed March 1, 2026, 1:10 a.m.
Created at: Feb. 28, 2026, 2:54 a.m.