Triple

T14057935
Position Surface form Disambiguated ID Type / Status
Subject Sosso state E338266 entity
Predicate language P15 FINISHED
Object Susu language E772784 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: Susu language | Statement: [Sosso state, language, Susu language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susu language
Context triple: [Sosso state, language, Susu language]
  • A. Susu language chosen
    Susu language is a Mande language of West Africa, primarily spoken by the Susu people in Guinea and neighboring countries.
  • B. Suku language
    Suku language is a Bantu language spoken primarily by the Suku people in the Democratic Republic of the Congo.
  • C. Suma language
    The Suma language is a lesser-known Gbaya language spoken by the Suma people in parts of Central Africa.
  • D. Suwawa language
    The Suwawa language is an Austronesian language spoken by the Suwawa people of northern Sulawesi, Indonesia, and is part of the Gorontalo–Mongondow subgroup.
  • E. Sialum language
    The Sialum language is a Papuan language spoken by the Sialum people of Morobe Province in Papua New Guinea.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de3c8e6d008190af8892f34c5cefbd completed April 14, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb662c37c8190a629278a97060080 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:20 p.m.