Triple

T22034756
Position Surface form Disambiguated ID Type / Status
Subject President of Malawi E544172 entity
Predicate officeHoldersInclude P537 FINISHED
Object Joyce Banda 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: Joyce Banda | Statement: [President of Malawi, officeHoldersInclude, Joyce Banda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joyce Banda
Context triple: [President of Malawi, officeHoldersInclude, Joyce Banda]
  • A. Joyce Banda chosen
    Joyce Banda is a Malawian politician who served as the country’s first female president from 2012 to 2014 and is known for her advocacy on women’s rights and good governance.
  • B. Linda Banda
    Linda Banda is an alternative name for the Banda-Linda language, a Central Sudanic language spoken in parts of Central Africa.
  • C. Lily Banda
    Lily Banda is a Malawian actress and artist best known for her role in the film "The Boy Who Harnessed the Wind."
  • D. Esther Lungu
    Esther Lungu is a Zambian public figure and former First Lady known for her charitable and social advocacy work during her husband Edgar Lungu’s presidency.
  • E. Maureen Mwanawasa
    Maureen Mwanawasa is a Zambian lawyer and former First Lady of Zambia known for her advocacy on health, women's rights, and social welfare issues.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127f0594881909caf4fbc3e0a2d50 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:25 p.m.