Triple

T13713726
Position Surface form Disambiguated ID Type / Status
Subject Afro-Bonaireans E328838 entity
Predicate language P15 FINISHED
Object Papiamentu E8930 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: Papiamentu | Statement: [Afro-Bonaireans, language, Papiamentu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Papiamentu
Context triple: [Afro-Bonaireans, language, Papiamentu]
  • A. Papiamento chosen
    Papiamento is a creole language primarily spoken in the Caribbean islands of Aruba, Curaçao, and Bonaire, with communities of speakers also found in parts of Europe and the Americas.
  • B. San Andrés–Providencia Creole
    San Andrés–Providencia Creole is an English-based Creole language spoken primarily on Colombia’s Caribbean islands of San Andrés, Providencia, and Santa Catalina.
  • C. Belizean Creole
    Belizean Creole is an English-based creole language widely spoken in Belize as a primary lingua franca and marker of national identity.
  • D. Dominican
    Dominican refers to members of the Catholic religious order founded by Saint Dominic, known for its emphasis on preaching, teaching, and theological scholarship.
  • E. Dominican
    Dominican refers to a person from Dominica, an island nation in the Caribbean known for its lush rainforests and 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd43973cf08190a417d0cca9dd314a completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7b0676e50819085fe48f86c0f93d8 completed May 3, 2026, 8:30 p.m.
Created at: April 9, 2026, 9:54 p.m.