Triple

T9337584
Position Surface form Disambiguated ID Type / Status
Subject Kwame E224682 entity
Predicate isNameOf P744 FINISHED
Object Kwame Darko E801586 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: Kwame Darko | Statement: [Kwame, isNameOf, Kwame Darko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kwame Darko
Context triple: [Kwame, isNameOf, Kwame Darko]
  • A. Kwame Agyapong
    Kwame Agyapong is a Ghanaian politician and businessman, best known as a long-serving Member of Parliament and influential figure in the New Patriotic Party.
  • B. Kofi Jamar
    Kofi Jamar is a Ghanaian rapper, singer, and songwriter known for his blend of hip hop, Afrobeat, and drill music.
  • C. Kwame Sefa Kayi
    Kwame Sefa Kayi is a prominent Ghanaian broadcast journalist and radio host, best known for anchoring the popular morning show "Kokrokoo" on Peace FM.
  • D. Kenneth Dadzie
    Kenneth Dadzie was a distinguished Ghanaian diplomat and international civil servant who served as Secretary-General of UNCTAD and played a key role in global trade and development policy.
  • E. Kwame Obeng Darko chosen
    Kwame Obeng Darko is a personal name, likely of Ghanaian origin, used by an individual whose specific public profile or notable achievements are not widely documented.
  • 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_69ca84286fcc81909f6e7fd7a7e862a2 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd37f312408190b5501432a6a855b7 completed April 1, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d190c570f08190ae8db5c82ed34b00 completed April 4, 2026, 10:29 p.m.
Created at: March 30, 2026, 7:40 p.m.