Triple

T2755607
Position Surface form Disambiguated ID Type / Status
Subject Bight of Biafra E61092 entity
Predicate hasPortCity P2745 FINISHED
Object Douala E132327 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: Douala | Statement: [Bight of Biafra, hasPortCity, Douala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douala
Context triple: [Bight of Biafra, hasPortCity, Douala]
  • A. Douala chosen
    Douala is the economic capital and main port city of Cameroon, located on the Wouri River along the Atlantic coast.
  • B. Yaoundé
    Yaoundé is the political and administrative center of Cameroon, known for its hilly terrain and role as a major cultural and economic hub in Central Africa.
  • C. Libreville
    Libreville is the largest city and main economic and cultural center of Gabon, located on the country’s Atlantic coast.
  • D. Pointe-Noire
    Pointe-Noire is a major port city on the Atlantic coast of the Republic of the Congo and one of the country’s principal economic and industrial centers.
  • E. Brazzaville
    Brazzaville is the capital and largest city of the Republic of the Congo, located on the Congo River directly across from Kinshasa in Central Africa.
  • 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_69ab4b7a85bc819094a349b84beb1f2c completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb718f4c8190bfc34c6597163ebc completed March 7, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69b1eed270f881909f907890f5fac412 completed March 11, 2026, 10:38 p.m.
Created at: March 6, 2026, 9:56 p.m.