Triple

T10505878
Position Surface form Disambiguated ID Type / Status
Subject Graça Simbine E247785 entity
Predicate name P16 FINISHED
Object Graça Simbine E247785 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: Graça Simbine | Statement: [Graça Simbine, name, Graça Simbine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graça Simbine
Context triple: [Graça Simbine, name, Graça Simbine]
  • A. Graça Simbine chosen
    Graça Simbine, better known as Graça Machel, is a Mozambican politician and humanitarian renowned for her advocacy on children's and women's rights and as the widow of both Samora Machel and Nelson Mandela.
  • B. Teshie Mantse
    Teshie Mantse is the traditional chief and paramount customary authority of the Teshie community in the Greater Accra Region of Ghana.
  • C. Sthandiwe Kgoroge
    Sthandiwe Kgoroge is a South African actress and television personality known for her roles in popular local dramas and soap operas.
  • D. Mary Masombuka
    Mary Masombuka is a central student activist character in the South African musical film and stage play "Sarafina!", symbolizing youth resistance against apartheid.
  • E. Lerato Radebe
    Lerato Radebe is an individual notable enough to be specifically cited as a bearer of the surname Radebe, though detailed public information about them is limited.
  • 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_69d381c4aa948190942e1d803143fb0e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509a07c908190bf0e3e5d480b306d completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dce30d788190b4a40340b9200b10 completed April 10, 2026, 11:20 a.m.
Created at: April 6, 2026, 12:26 p.m.