Triple

T23022947
Position Surface form Disambiguated ID Type / Status
Subject Khaling language E573216 entity
Predicate subgroup P10 FINISHED
Object Kiranti 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: Kiranti | Statement: [Khaling language, subgroup, Kiranti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiranti
Context triple: [Khaling language, subgroup, Kiranti]
  • A. Kiranti chosen
    Kiranti is a group of closely related Sino-Tibetan languages spoken primarily by the Kirati ethnic communities in eastern Nepal.
  • B. Arihant
    Arihant is a Sanskrit term in Jainism referring to a soul that has conquered inner passions and attained perfect knowledge, but not yet final liberation.
  • C. Kothari
    Kothari is an Indian surname commonly associated with various notable figures in fields such as science, business, and public life.
  • D. Sankhali
    Sankhali is a village located in the North Goa district of the Indian state of Goa.
  • E. Kala Kosa
    Kala Kosa is a specialized research and documentation division of the Indira Gandhi National Centre for the Arts focused on the study and preservation of Indian art, culture, and textual traditions.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183ea23088190b2f42d9bf01514ac completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.