Triple

T2239222
Position Surface form Disambiguated ID Type / Status
Subject Polynesians E49353 entity
Predicate hasLanguage P15 FINISHED
Object Wallisian language E145898 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: Wallisian language | Statement: [Polynesians, hasLanguage, Wallisian language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wallisian language
Context triple: [Polynesians, hasLanguage, Wallisian language]
  • A. Wallisian language chosen
    The Wallisian language is an Austronesian Polynesian language spoken primarily on Wallis Island (Uvea) in the French overseas collectivity of Wallis and Futuna.
  • B. Waigali language
    The Waigali language is a Nuristani language spoken by the Waigal people in eastern Afghanistan.
  • C. North Marquesan language
    North Marquesan is an Eastern Polynesian language spoken primarily in the northern Marquesas Islands of French Polynesia.
  • D. Manus languages
    Manus languages are a group of closely related Oceanic Austronesian languages spoken primarily on Manus Island and nearby islands in Papua New Guinea.
  • E. Vella Lavella language
    The Vella Lavella language is an Oceanic language spoken by the indigenous population of Vella Lavella Island in the Western Province of the Solomon Islands.
  • 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_69ae6b0cb4f0819087061434d44dc3a3 completed March 9, 2026, 6:39 a.m.
Created at: March 4, 2026, 7:47 p.m.