Triple

T1012674
Position Surface form Disambiguated ID Type / Status
Subject Kiunguja E21856 entity
Predicate associatedCity P3207 FINISHED
Object Zanzibar City
Zanzibar City is the historic and administrative capital of Zanzibar, Tanzania, renowned for its UNESCO-listed Stone Town and rich Swahili, Arab, and colonial heritage.
E122501 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: Zanzibar City | Statement: [Kiunguja, associatedCity, Zanzibar City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zanzibar City
Context triple: [Kiunguja, associatedCity, Zanzibar City]
  • A. Dar es Salaam
    Dar es Salaam is a major coastal metropolis on the Indian Ocean and the principal economic and commercial hub of Tanzania.
  • B. Mombasa
    Mombasa is a major coastal city in Kenya known as a key regional port and historic trading hub on the Indian Ocean.
  • C. Moshi
    Moshi is a Tanzanian town in the Kilimanjaro Region that serves as a major gateway and base for climbers ascending Mount Kilimanjaro.
  • D. Dodoma
    Dodoma is the political and administrative capital city of Tanzania, located in the country’s central region.
  • E. Arusha, Tanzania
    Arusha, Tanzania is a major city in northern Tanzania known as a diplomatic hub and gateway to popular safari destinations and Mount Kilimanjaro.
  • 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: Zanzibar City
Triple: [Kiunguja, associatedCity, Zanzibar City]
Generated description
Zanzibar City is the historic and administrative capital of Zanzibar, Tanzania, renowned for its UNESCO-listed Stone Town and rich Swahili, Arab, and colonial heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zanzibar City
Target entity description: Zanzibar City is the historic and administrative capital of Zanzibar, Tanzania, renowned for its UNESCO-listed Stone Town and rich Swahili, Arab, and colonial heritage.
  • A. Dar es Salaam
    Dar es Salaam is a major coastal metropolis on the Indian Ocean and the principal economic and commercial hub of Tanzania.
  • B. Mombasa
    Mombasa is a major coastal city in Kenya known as a key regional port and historic trading hub on the Indian Ocean.
  • C. Moshi
    Moshi is a Tanzanian town in the Kilimanjaro Region that serves as a major gateway and base for climbers ascending Mount Kilimanjaro.
  • D. Dodoma
    Dodoma is the political and administrative capital city of Tanzania, located in the country’s central region.
  • E. Arusha, Tanzania
    Arusha, Tanzania is a major city in northern Tanzania known as a diplomatic hub and gateway to popular safari destinations and Mount Kilimanjaro.
  • 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_69a493c68e24819080ed0ee8bcfd5ce0 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7a8b254819089ffed9cb62a6930 completed March 1, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3bad654c81909dd59211fafa8b2c completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3c41ab70819090084c508dbfd295 completed March 7, 2026, 2:54 p.m.
NED2 Entity disambiguation (via description) batch_69ac3cbb30d081909759df25c21eb275 completed March 7, 2026, 2:56 p.m.
Created at: March 1, 2026, 7:41 p.m.