Triple

T9605937
Position Surface form Disambiguated ID Type / Status
Subject Jimmy Akena E231970 entity
Predicate relative P37 FINISHED
Object Miria Obote E810833 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: Miria Obote | Statement: [Jimmy Akena, relative, Miria Obote]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miria Obote
Context triple: [Jimmy Akena, relative, Miria Obote]
  • A. Miria Obote chosen
    Miria Obote is a Ugandan politician and former First Lady who led the Uganda People's Congress after the death of her husband, former president Milton Obote.
  • B. Tindyebwa Agaba Wise
    Tindyebwa Agaba Wise is a Rwandan-born British activist and former child soldier who became known for his work on human rights and refugee issues after being adopted by actress Emma Thompson.
  • C. Maria Nyerere
    Maria Nyerere is the widow of Tanzania’s founding president Julius Nyerere and a prominent Tanzanian public figure known for her role in national and social affairs.
  • D. Ida Odinga
    Ida Odinga is a Kenyan businesswoman, educator, and prominent political activist, best known for her influential role in Kenya’s pro-democracy movement and public life.
  • E. Florence Kasumba
    Florence Kasumba is a Ugandan-German actress known for her roles in international film and television, including appearances in the Marvel Cinematic Universe and various high-profile German productions.
  • 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_69ca8484838c8190b2049199d22fef70 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a6006d48190adc03306533b9be6 completed April 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d189f215588190ac04a3b0e3337807 completed April 4, 2026, 10 p.m.
Created at: March 30, 2026, 8:08 p.m.