Triple

T5442927
Position Surface form Disambiguated ID Type / Status
Subject MSG E122179 entity
Predicate officialLanguage P236 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: [MSG, officialLanguage, Bislama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bislama
Context triple: [MSG, officialLanguage, 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_69bd4640f52c81909e653ec361f66d76 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91cb5eec8190bdf2ef0bdea84a62 completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf41302d588190afa5906d0e3dd891 completed March 22, 2026, 1:09 a.m.
Created at: March 20, 2026, 2:07 p.m.