Triple

T5336514
Position Surface form Disambiguated ID Type / Status
Subject Accra III Agreement E123839 entity
Predicate signedInCity P4488 FINISHED
Object Accra E68377 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: Accra | Statement: [Accra III Agreement, signedInCity, Accra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Accra
Context triple: [Accra III Agreement, signedInCity, Accra]
  • A. Accra chosen
    Accra is the capital and largest city of Ghana, known as a major economic, political, and cultural hub in West Africa.
  • B. Takoradi
    Takoradi is a coastal city in southwestern Ghana that developed into a key commercial and industrial hub, particularly known for its deep-water seaport and role in regional trade.
  • C. Kumasi
    Kumasi is a major city in southern Ghana, known as the historic capital of the Ashanti Kingdom and a key cultural and commercial center in West Africa.
  • D. Serekunda
    Serekunda is the most populous urban center and a major commercial hub in The Gambia.
  • E. Winneba, Ghana
    Winneba, Ghana is a coastal town in the Central Region of Ghana known for its fishing industry, Aboakyer festival, and the University of Education, Winneba.
  • 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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85b104c081908b81236a0142e1c8 completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18c1e1f88190a47489a9491eaf08 completed March 21, 2026, 10:16 p.m.
Created at: March 20, 2026, 2 p.m.