Triple

T14010549
Position Surface form Disambiguated ID Type / Status
Subject Nupoid E337065 entity
Predicate hasMember P10 FINISHED
Object Shama language (Nupoid) E337060 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: Shama language (Nupoid) | Statement: [Nupoid, hasMember, Shama language (Nupoid)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shama language (Nupoid)
Context triple: [Nupoid, hasMember, Shama language (Nupoid)]
  • A. Nupoid languages chosen
    Nupoid languages are a subgroup of the Volta–Niger branch of the Niger–Congo language family spoken primarily in central Nigeria, including the Nupe language and its close relatives.
  • B. Chamalal language
    The Chamalal language is a Northeast Caucasian language spoken by the Chamalal people in the western part of Dagestan, Russia.
  • C. Shompen language
    Shompen language is an endangered and poorly documented Austroasiatic language spoken by the indigenous Shompen people of Great Nicobar Island in India.
  • D. Kamang language
    The Kamang language is a Papuan language spoken by communities on the Alor archipelago in eastern Indonesia.
  • E. Chamling language
    The Chamling language is a Kiranti Sino-Tibetan language spoken primarily by the Chamling Rai people of eastern Nepal.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed5cfd0819085b9c860b119a9de completed April 14, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc32b459c81908b652286f444e940 completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:19 p.m.