Triple

T2346670
Position Surface form Disambiguated ID Type / Status
Subject Yapese E45146 entity
Predicate hasNativeName P1435 FINISHED
Object Yapese E45146 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: Yapese | Statement: [Yapese, hasNativeName, Yapese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yapese
Context triple: [Yapese, hasNativeName, Yapese]
  • A. Yapese chosen
    Yapese is an Austronesian language spoken primarily on the island of Yap and nearby islands in the western Pacific.
  • B. Okinawan Japanese
    Okinawan Japanese is a regional variety of the Japanese language spoken primarily in Okinawa, influenced by both Standard Japanese and the indigenous Ryukyuan languages.
  • C. Okinawan language
    The Okinawan language is a Ryukyuan language of the Japonic family traditionally spoken in Okinawa, known for its distinct phonology, vocabulary, and grammar that differ significantly from standard Japanese.
  • D. Yaeyama language
    The Yaeyama language is a Southern Ryukyuan language spoken in Japan’s Yaeyama Islands, distinct from standard Japanese and recognized as endangered.
  • E. Japanese
    Japanese is the national language of Japan, a Japonic language known for its complex writing system combining kanji and kana.
  • 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_69a88917935081909b755dbf38e81024 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc6c9396081908abb2b0a229bb046 completed March 7, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9629f4908190ba3c51b7d12be4e4 completed March 9, 2026, 9:43 a.m.
Created at: March 4, 2026, 7:52 p.m.