Triple

T6854643
Position Surface form Disambiguated ID Type / Status
Subject Ryukyuan music E158106 entity
Predicate language P15 FINISHED
Object Amami language E135027 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: Amami language | Statement: [Ryukyuan music, language, Amami language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amami language
Context triple: [Ryukyuan music, language, Amami language]
  • A. Amami language chosen
    The Amami language is a Ryukyuan language spoken in Japan’s Amami Islands, known for its endangered status and distinct phonology and grammar within the Japonic language family.
  • B. Akawaio language
    The Akawaio language is an indigenous Cariban language spoken by the Akawaio people of Guyana, Venezuela, and Brazil.
  • C. Tanema language
    Tanema is a nearly extinct Oceanic language once spoken on Vanikoro Island in the Temotu Province of the Solomon Islands.
  • D. Unami language
    The Unami language is an Eastern Algonquian Native American language traditionally spoken by the Lenape (Delaware) people in the mid-Atlantic region of the United States.
  • E. Miyako language
    The Miyako language is a Southern Ryukyuan language of Japan’s Okinawa Prefecture, spoken primarily on the Miyako Islands and noted for its distinct phonology and endangered status.
  • 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_69c6882fae988190864cbba788c5ebb4 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d86d5a54819088537ada9f8d1105 completed March 27, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fdda9cc8190b039f892d046d7af completed March 28, 2026, 1:33 a.m.
Created at: March 27, 2026, 2:20 p.m.