Triple

T800692
Position Surface form Disambiguated ID Type / Status
Subject Sub-Saharan Africa E17120 entity
Predicate contains P35 FINISHED
Object Lesotho E15906 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: Lesotho | Statement: [Sub-Saharan Africa, contains, Lesotho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lesotho
Context triple: [Sub-Saharan Africa, contains, Lesotho]
  • A. Lesotho chosen
    Lesotho is a small, landlocked constitutional monarchy in Southern Africa, entirely surrounded by South Africa and known for its mountainous terrain and high-altitude settlements.
  • B. Eswatini
    Eswatini is a small landlocked monarchy in Southern Africa known for its blend of traditional Swazi culture and modern institutions.
  • C. Botswana
    Botswana is a landlocked country in Southern Africa known for its stable democracy, significant diamond resources, and vast wildlife-rich landscapes including the Okavango Delta.
  • D. Botswana and Zimbabwe
    Botswana and Zimbabwe are neighboring landlocked countries in Southern Africa that share close historical, economic, and ecological ties.
  • E. Namibia
    Namibia is a sparsely populated country in southwestern Africa known for its dramatic desert landscapes, diverse wildlife, and a legal system influenced by Roman-Dutch law.
  • 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_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cc75e88190bd35aabe51051b51 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69add197c5248190ae37a11693975f97 completed March 8, 2026, 7:44 p.m.
Created at: March 1, 2026, 7:38 p.m.