Triple

T376170
Position Surface form Disambiguated ID Type / Status
Subject Gabon E8377 entity
Predicate largestCity P235 FINISHED
Object Libreville E47980 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: Libreville | Statement: [Gabon, largestCity, Libreville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Libreville
Context triple: [Gabon, largestCity, Libreville]
  • A. Libreville chosen
    Libreville is the largest city and main economic and cultural center of Gabon, located on the country’s Atlantic coast.
  • B. 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.
  • C. Luanda
    Luanda is the capital and largest city of Angola, a major Atlantic port and economic hub with a history shaped by Portuguese colonial rule and the transatlantic slave trade.
  • D. Dakar
    Dakar is the capital and largest city of Senegal, located on the Atlantic coast and serving as a major political, economic, and cultural hub of West Africa.
  • E. Monrovia
    Monrovia is the largest city and main economic and administrative center of Liberia, located on the Atlantic coast in West 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_69a2e7f2ec648190b42bc7db424f8109 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec169a848190a577aa093c878839 completed Feb. 28, 2026, 1:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3fafca1dc8190ba8f1cdec0ba337d completed March 1, 2026, 8:38 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.