Triple

T2239087
Position Surface form Disambiguated ID Type / Status
Subject Tok Pisin E49351 entity
Predicate closelyRelatedTo P37 FINISHED
Object Bislama E153026 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: Bislama | Statement: [Tok Pisin, closelyRelatedTo, Bislama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bislama
Context triple: [Tok Pisin, closelyRelatedTo, Bislama]
  • A. Bislama chosen
    Bislama is an English-based creole language widely spoken in Vanuatu and used as a key lingua franca across its many islands and communities.
  • B. Kapingamarangi language
    The Kapingamarangi language is a Polynesian outlier language spoken primarily on Kapingamarangi Atoll in the Federated States of Micronesia.
  • C. Mari language
    The Mari language is a Uralic language spoken primarily by the Mari people in the Mari El Republic and surrounding regions of Russia, known for its distinct dialects and rich oral tradition.
  • D. Romblomanon language
    Romblomanon language is an Austronesian language spoken primarily on the island of Romblon and nearby areas in the central Philippines.
  • E. Fala language
    Fala is a small Ibero-Romance language spoken in a few villages in Spain’s Extremadura region, notable for its close relation to Galician-Portuguese and its strong local identity.
  • 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_69a88aa84bdc819086df50e9c20b301e completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0bb3fac81908b1e8518951dd160 completed March 7, 2026, 6:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b0a9ee881909dee8b0a657b9c73 completed March 9, 2026, 6:39 a.m.
Created at: March 4, 2026, 7:47 p.m.