Triple

T16356094
Position Surface form Disambiguated ID Type / Status
Subject Manzini E397182 entity
Predicate locatedIn P40 FINISHED
Object Manzini Region E649375 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: Manzini Region | Statement: [Manzini, locatedIn, Manzini Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manzini Region
Context triple: [Manzini, locatedIn, Manzini Region]
  • A. Manzini Region chosen
    Manzini Region is one of Eswatini’s four administrative regions, centrally located and home to the country’s largest urban and commercial center, Manzini city.
  • B. Ruvuma Region
    Ruvuma Region is a largely rural administrative area in southern Tanzania known for its wildlife, forests, and proximity to major conservation areas.
  • C. Nkomazi region
    The Nkomazi region is a largely rural area in eastern South Africa known for its agriculture, scenic landscapes, and proximity to the borders with Mozambique and Eswatini.
  • D. Vhembe region
    The Vhembe region is a predominantly rural area in the northernmost part of South Africa’s Limpopo Province, known for its rich Venda cultural heritage, agricultural activities, and proximity to borders with Zimbabwe and Mozambique.
  • E. Lindi Region
    Lindi Region is a coastal administrative region in southern Tanzania known for its historical Swahili settlements and Indian Ocean shoreline.
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2facf67e0819089a23ce6f5642fbe completed April 18, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003c50763881908b115953961efef9 completed May 10, 2026, 8:05 a.m.
Created at: April 10, 2026, 5:07 a.m.