Triple

T23283413
Position Surface form Disambiguated ID Type / Status
Subject Islamic State of the Greater Sahara E588926 entity
Predicate countryOfOrigin P26 FINISHED
Object Niger NE NERFINISHED

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: Niger | Statement: [Islamic State of the Greater Sahara, countryOfOrigin, Niger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Niger
Context triple: [Islamic State of the Greater Sahara, countryOfOrigin, Niger]
  • A. Niger chosen
    Niger is a landlocked West African country in the Sahel region, known for its vast desert landscapes, uranium resources, and predominantly rural population.
  • B. 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.
  • C. Mali
    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.
  • D. Mali
    Mali is a village located on the island of New Ireland in Papua New Guinea.
  • E. Río de Oro
    Río de Oro is a river in northeastern Colombia that flows through the Santander region and passes near the city of Bucaramanga.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d16e2c08190a291de254703129e completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196447a748190bd797ec9baa63fc3 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 4:58 p.m.