Triple

T6988565
Position Surface form Disambiguated ID Type / Status
Subject Constitutive Act of the African Union E162027 entity
Predicate adoptionPlace P1677 FINISHED
Object Lomé, Togo E71688 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: Lomé, Togo | Statement: [Constitutive Act of the African Union, adoptionPlace, Lomé, Togo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lomé, Togo
Context triple: [Constitutive Act of the African Union, adoptionPlace, Lomé, Togo]
  • A. Lomé chosen
    Lomé is the coastal capital and largest city of Togo, serving as a key economic and cultural hub in West Africa.
  • B. Serekunda
    Serekunda is the most populous urban center and a major commercial hub in The Gambia.
  • C. Libreville
    Libreville is the largest city and main economic and cultural center of Gabon, located on the country’s Atlantic coast.
  • D. Port-Gentil
    Port-Gentil is Gabon's second-largest city and a major oil and port hub located on the country's Atlantic coast.
  • E. Bertoua
    Bertoua is a major city in eastern Cameroon that serves as an important administrative and commercial hub for the surrounding forested region.
  • 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_69c68856d7808190ab33ee914640281b completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dbbd926c8190a8b60527bd553fa3 completed March 27, 2026, 7:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761d3f07081908892cdcac8e0917c completed March 28, 2026, 5:06 a.m.
Created at: March 27, 2026, 2:32 p.m.