Triple

T2420502
Position Surface form Disambiguated ID Type / Status
Subject Ssese Islands E53406 entity
Predicate locatedIn P40 FINISHED
Object Central Uganda E203299 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: Central Uganda | Statement: [Ssese Islands, locatedIn, Central Uganda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Central Uganda
Context triple: [Ssese Islands, locatedIn, Central Uganda]
  • A. Central Region, Uganda chosen
    Central Region, Uganda is the country’s most populous and economically significant region, encompassing the capital city Kampala and serving as a major hub for administration, commerce, and culture.
  • B. Shinyanga Region
    Shinyanga Region is an administrative region in northwestern Tanzania known for its agriculture, mining activities, and proximity to Lake Victoria.
  • C. Kagera Region
    Kagera Region is a northwestern region of Tanzania bordering Lake Victoria and several East African countries, known for its diverse ethnic groups, agriculture, and historical significance.
  • D. Mafinga Central
    Mafinga Central is a mountainous region in northeastern Zambia that contains the country’s highest elevations within the Mafinga Hills.
  • E. Uganda
    Uganda is a landlocked country in East Africa known for its diverse landscapes, abundant wildlife, and location along the equator.
  • 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_69ab495c44d48190b7235b23719bc3f6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc96f97e08190978b2d873ab88859 completed March 7, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf57b0708190bf4d38c51e02309f completed March 9, 2026, 12:38 p.m.
Created at: March 6, 2026, 9:42 p.m.