Triple

T2712610
Position Surface form Disambiguated ID Type / Status
Subject Jos E59896 entity
Predicate locatedOn P40 FINISHED
Object Jos Plateau E289553 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: Jos Plateau | Statement: [Jos, locatedOn, Jos Plateau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jos Plateau
Context triple: [Jos, locatedOn, Jos Plateau]
  • A. Jos Plateau chosen
    Jos Plateau is a highland region in central Nigeria known for its cool climate, scenic landscapes, and rich mineral resources, especially tin.
  • B. Langres Plateau
    The Langres Plateau is a high limestone upland in northeastern France known as a major watershed that gives rise to several important rivers, including the Seine.
  • C. Montmorency plateau
    The Montmorency plateau is a raised geographic area in the Val-d'Oise department of northern France, known for its suburban communities overlooking the Paris metropolitan region.
  • D. Feneos plateau
    The Feneos plateau is a highland plain in the northern Peloponnese of Greece, known for its karstic fields, seasonal lake, and surrounding mountain scenery.
  • E. Sanetti Plateau
    Sanetti Plateau is a high-altitude Afro-alpine plateau in Ethiopia’s Bale Mountains, known for its unique biodiversity and dramatic volcanic landscapes.
  • 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_69ab4ac92a088190bc74bca14038e3de completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda90d5a88190bcb6caefd8f2dd1b completed March 7, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb68552848190ad2e615e16716fa1 completed March 10, 2026, 6:13 a.m.
Created at: March 6, 2026, 9:55 p.m.