Triple

T14857728
Position Surface form Disambiguated ID Type / Status
Subject Kankan E349403 entity
Predicate languageUsed P238 FINISHED
Object Maninka language E351830 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: Maninka language | Statement: [Kankan, languageUsed, Maninka language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maninka language
Context triple: [Kankan, languageUsed, Maninka language]
  • A. Mandinka language chosen
    The Mandinka language is a Mande language of West Africa widely spoken in countries such as Gambia, Senegal, Guinea, and Mali, and serves as a major lingua franca of the Mandinka people.
  • B. Banda-Mbrém language
    The Banda-Mbrém language is a Central Sudanic language spoken by the Banda people in parts of Central Africa, particularly in the Central African Republic.
  • C. Sanglechi language
    The Sanglechi language is an Eastern Iranian language spoken by a small community in the Sanglech Valley region of Afghanistan and Tajikistan.
  • D. Mandeali language
    Mandeali language is an Indo-Aryan language spoken primarily in the Mandi region of Himachal Pradesh, India.
  • E. Tindi language
    The Tindi language is a Northeast Caucasian language spoken by the Tindi people in Dagestan, Russia, known for its complex grammar and limited number of speakers.
  • 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_69d822ed7e1881909b90fca143ad7e34 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded44458ec8190be295a95f5daab14 completed April 14, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe650a43bc8190b836fe690d2a3c71 completed May 8, 2026, 10:34 p.m.
Created at: April 10, 2026, 1:54 a.m.