Triple

T499962
Position Surface form Disambiguated ID Type / Status
Subject Sahara Desert E10378 entity
Predicate locatedIn P40 FINISHED
Object Mali E40373 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: Mali | Statement: [Sahara Desert, locatedIn, Mali]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mali
Context triple: [Sahara Desert, locatedIn, Mali]
  • A. Mali chosen
    Mali is a landlocked West African country known for its historic trading cities like Timbuktu, rich Sahelian culture, and significant role in the ancient Mali Empire.
  • B. Burkina Faso
    Burkina Faso is a landlocked West African country known for its diverse cultures, Sahelian landscapes, and capital city, Ouagadougou.
  • C. Mauritania
    Mauritania is a Northwest African country on the Atlantic coast, known for its vast Saharan landscapes, mixed Arab-Berber and Sub-Saharan cultures, and significant iron ore resources.
  • D. Senegal
    Senegal is a West African country on the Atlantic coast known for its vibrant culture, historic role in transatlantic trade, and diverse coastal and Sahelian landscapes.
  • E. Guinea
    Guinea is a West African country on the Atlantic coast known for its rich mineral resources, diverse ethnic groups, and role as a major producer of bauxite.
  • 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f13096248190a622a58dcf540b00 completed Feb. 28, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad158273188190ba7d9005161f4a70 completed March 8, 2026, 6:21 a.m.
Created at: Feb. 28, 2026, 1:12 p.m.