Triple

T11783181
Position Surface form Disambiguated ID Type / Status
Subject Mordvins E280201 entity
Predicate language P15 FINISHED
Object Moksha language E149565 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: Moksha language | Statement: [Mordvins, language, Moksha language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moksha language
Context triple: [Mordvins, language, Moksha language]
  • A. Moksha language chosen
    The Moksha language is a Uralic language spoken primarily by the Moksha people in central Russia, noted for its complex grammar and close relation to the Erzya language.
  • B. Mota language
    Mota language is an Oceanic language of Vanuatu historically notable as an early Christian mission lingua franca in the region.
  • C. Momo languages
    Momo languages are a small subgroup of Bantoid languages spoken in western Cameroon, closely related to other Grassfields languages.
  • D. Moxo language
    The Moxo language is an indigenous Arawakan language spoken by the Moxo (Mojo) people of Bolivia’s lowland regions.
  • E. Molbog language
    The Molbog language is an Austronesian language spoken by the Molbog people of southern Palawan in the Philippines and parts of northern Borneo.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a58413048190b9e3b9d2f5383ec3 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f090d861f481909b920197a3d60e28 completed April 28, 2026, 10:50 a.m.
Created at: April 8, 2026, 9:42 p.m.