Triple

T14998611
Position Surface form Disambiguated ID Type / Status
Subject Tanga Region E374023 entity
Predicate borders P224 FINISHED
Object Manyara Region E375327 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: Manyara Region | Statement: [Tanga Region, borders, Manyara Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manyara Region
Context triple: [Tanga Region, borders, Manyara Region]
  • A. Manyara Region chosen
    Manyara Region is an administrative region in northern Tanzania known for its wildlife-rich Lake Manyara National Park and diverse landscapes ranging from rift valley escarpments to savannah.
  • B. Mafinga region
    Mafinga Region is an administrative area in Tanzania that includes Mafinga Central and surrounding localities.
  • C. Nyanza region
    Nyanza region is an area in western Kenya along Lake Victoria, known for its predominantly Luo population and the city of Kisumu as its main urban center.
  • D. Kilimanjaro Region
    Kilimanjaro Region is an administrative area in northeastern Tanzania best known for encompassing Africa’s highest peak, Mount Kilimanjaro, and serving as a major hub for tourism and agriculture.
  • E. Omaheke Region
    Omaheke Region is an administrative region in eastern Namibia known for its semi-arid savannah landscapes and cattle farming.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded71a5618819083ae96a79735ef98 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef888a7988190837f3f4b8d340e04 completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 2:54 a.m.