Triple

T23505980
Position Surface form Disambiguated ID Type / Status
Subject Nyishi language E572281 entity
Predicate closelyRelatedTo P37 FINISHED
Object Galo 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: Galo language | Statement: [Nyishi language, closelyRelatedTo, Galo language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Galo language
Context triple: [Nyishi language, closelyRelatedTo, Galo language]
  • A. Galo language chosen
    Galo language is a Tibeto-Burman language spoken primarily by the Galo people in Arunachal Pradesh, India.
  • B. Gallo language
    Gallo language is a regional Romance language of eastern Brittany in France, distinct from both Breton and standard French.
  • C. Galela language
    The Galela language is an Austronesian language spoken by the Galela people in northern Halmahera, Indonesia.
  • D. Gabrielino language
    The Gabrielino language, also known as Tongva, is an Uto-Aztecan Indigenous language historically spoken by the Tongva people of the Los Angeles Basin and Southern Channel Islands in California.
  • E. Mari language
    The Mari language is a Uralic language spoken primarily by the Mari people in the Mari El Republic and surrounding regions of Russia, known for its distinct dialects and rich oral tradition.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a9009ca081908c4cffb8c32293ec completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:07 p.m.