Triple

T15189781
Position Surface form Disambiguated ID Type / Status
Subject Omani Empire E362977 entity
Predicate capital P234 FINISHED
Object Zanzibar City E122501 NE FINISHED

How this triple was built (2 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: [Omani Empire, capital, Zanzibar City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zanzibar City
Context triple: [Omani Empire, capital, Zanzibar City]
  • A. Zanzibar City chosen
    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.
  • B. Dar es Salaam
    Dar es Salaam is a major coastal metropolis on the Indian Ocean and the principal economic and commercial hub of Tanzania.
  • C. Likasi
    Likasi is a mining city in the southeastern Democratic Republic of the Congo, known for its significant copper and cobalt production.
  • D. Mombasa
    Mombasa is a major coastal city in Kenya known as a key regional port and historic trading hub on the Indian Ocean.
  • E. Moshi
    Moshi is a Tanzanian town in the Kilimanjaro Region that serves as a major gateway and base for climbers ascending Mount Kilimanjaro.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85a09a39c81908759f23268e2d408 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0067beedc8190abc0a94c7a38f85e completed April 15, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd2bff388190881396685edd1787 completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 3:10 a.m.