Triple

T14788505
Position Surface form Disambiguated ID Type / Status
Subject Southern Niger E347591 entity
Predicate contains P35 FINISHED
Object Dosso Region E1098033 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: Dosso Region | Statement: [Southern Niger, contains, Dosso Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dosso Region
Context triple: [Southern Niger, contains, Dosso Region]
  • A. Dosso Region chosen
    Dosso Region is an administrative region in southwestern Niger known for its agricultural activities and proximity to the capital, Niamey.
  • B. Vanni region
    The Vanni region is a largely rural and forested area in northern Sri Lanka that became a major stronghold of the LTTE and a central battleground during the Sri Lankan civil war.
  • C. Elis region
    The Elis region is a historical area in western Peloponnese, Greece, known in antiquity for encompassing the city-state that administered the sanctuary of Olympia and the ancient Olympic Games.
  • D. Lunigiana
    Lunigiana is a historical region in northwestern Italy, spanning parts of Tuscany and Liguria, known for its medieval castles, hilltop villages, and rugged Apennine landscapes.
  • E. Valdelsa
    Valdelsa is a historical valley area in Tuscany, Italy, known for its medieval hill towns, agricultural landscapes, and cultural heritage.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decaa1e9ec81908d7c26c1c4e43014 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24b9e8a08190bc736ac207b77324 completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:31 a.m.