Triple

T21160706
Position Surface form Disambiguated ID Type / Status
Subject MSG Secretariat E521432 entity
Predicate languageUsed P238 FINISHED
Object Bislama NE NERFINISHED

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 Secretariat, languageUsed, Bislama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bislama
Context triple: [MSG Secretariat, languageUsed, 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. Wuvulu-Aua language
    The Wuvulu-Aua language is an Oceanic language spoken on the Wuvulu and Aua islands of Papua New Guinea, known for its complex verbal morphology and distinctive phonological features.
  • C. Kapingamarangi language
    The Kapingamarangi language is a Polynesian outlier language spoken primarily on Kapingamarangi Atoll in the Federated States of Micronesia.
  • D. Kacipo-Bale language
    The Kacipo-Bale language is a Surmic language spoken by the Kacipo and Bale peoples of southwestern Ethiopia and neighboring regions of South Sudan.
  • E. Agutaynen language
    Agutaynen is an Austronesian language spoken by the Agutaynen people of Palawan in the Philippines.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7252f70888190b8e6109cc4099ecc completed April 21, 2026, 7:20 a.m.
Created at: April 16, 2026, 2:59 p.m.