Triple

T20628002
Position Surface form Disambiguated ID Type / Status
Subject Lugazi E506870 entity
Predicate near P350 FINISHED
Object Mabira Forest NE NERFINISHED

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: Mabira Forest | Statement: [Lugazi, near, Mabira Forest]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mabira Forest
Context triple: [Lugazi, near, Mabira Forest]
  • A. Mabira Forest chosen
    Mabira Forest is a large tropical rainforest in central Uganda known for its rich biodiversity, ecotourism activities, and role as a key conservation area between Kampala and Jinja.
  • B. Budongo Forest
    Budongo Forest is a large tropical rainforest in western Uganda renowned for its rich biodiversity, especially its chimpanzee population and extensive mahogany trees.
  • C. Kasane Forest Reserve
    Kasane Forest Reserve is a protected woodland area in northern Botswana known for its rich wildlife and proximity to the Chobe River and Chobe National Park.
  • D. Maramagambo Forest
    Maramagambo Forest is a large tropical rainforest in western Uganda known for its rich biodiversity, crater lakes, and extensive network of caves.
  • E. Kibale National Park
    Kibale National Park is a renowned protected area in western Uganda famous for its rich tropical rainforest and one of Africa’s highest concentrations of primates, especially chimpanzees.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4bd4a0081908d4e97a590a33fb2 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6abe645888190b639ebedc5b3041a completed April 20, 2026, 10:42 p.m.
Created at: April 16, 2026, 11:42 a.m.