Triple

T23409070
Position Surface form Disambiguated ID Type / Status
Subject Amis E560014 entity
Predicate language P15 FINISHED
Object Amis language 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: Amis language | Statement: [Amis, language, Amis language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amis language
Context triple: [Amis, language, Amis language]
  • A. Amis language chosen
    The Amis language is an Austronesian language spoken by the Amis people of eastern Taiwan and is one of the largest and most vital of the island’s Indigenous languages.
  • B. Amuesha language
    The Amuesha language, also known as Yanesha', is an Arawakan language spoken by the Yanesha' people of the central Peruvian Amazon.
  • C. Amandinois
    Amandinois is the French demonym for inhabitants of the town of Saint-Amand-les-Eaux in northern France.
  • D. Nomatsiguenga language
    The Nomatsiguenga language is an Arawakan language spoken by the Nomatsiguenga people of Peru’s Amazon rainforest, closely associated with the broader Asháninka linguistic and cultural group.
  • E. Proto-Amis
    Proto-Amis is the reconstructed ancestral form of the Amis language from which modern Southern Amis and other dialects are derived.
  • 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_69e2454b3a5881909c64773dc8a5d289 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a50fff10819094e71fb0c11b7d95 completed April 29, 2026, 6:28 a.m.
Created at: April 17, 2026, 5:38 p.m.