Triple

T12697438
Position Surface form Disambiguated ID Type / Status
Subject Ndyuka E303371 entity
Predicate selfDesignation P974 FINISHED
Object Okanisi E604535 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: Okanisi | Statement: [Ndyuka, selfDesignation, Okanisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Okanisi
Context triple: [Ndyuka, selfDesignation, Okanisi]
  • A. Okanisi chosen
    Okanisi is another name for the Ndyuka Maroons, a community of African-descended people in Suriname and French Guiana known for their distinct language and culture formed through resistance to slavery.
  • B. Sawusea
    Sawusea, also known as the Savu Sea, is a small sea in the western Pacific Ocean located between the islands of Indonesia, including Timor, Sumba, and Flores.
  • C. Fenua Loa
    Fenua Loa is the largest and main island of the remote Duff Islands group in the Solomon Islands.
  • D. Ulawa
    Ulawa is a small island in the Solomon Islands’ Makira-Ulawa Province, known for its rural villages, subsistence lifestyle, and surrounding coral reefs.
  • E. Oze
    Oze is a small river in France that serves as a left-bank tributary of the Armançon.
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ed26588190ae76ff17159e06ec completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671b066348190aedfe186fc4724f9 completed May 2, 2026, 9:50 p.m.
Created at: April 9, 2026, 5:22 p.m.