Triple

T22850211
Position Surface form Disambiguated ID Type / Status
Subject Qiangic group E566336 entity
Predicate hasPart P35 FINISHED
Object Situ Rgyalrong 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: Situ Rgyalrong | Statement: [Qiangic group, hasPart, Situ Rgyalrong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Situ Rgyalrong
Context triple: [Qiangic group, hasPart, Situ Rgyalrong]
  • A. Rgyalrong chosen
    Rgyalrong is a group of closely related Sino-Tibetan languages spoken primarily in western Sichuan, China, known for their complex morphology and conservative phonological features.
  • B. Tso Ngön
    Tso Ngön is the Tibetan name for Qinghai Lake, a large saline lake on the northeastern Tibetan Plateau in China.
  • C. Dungsam Tsangla
    Dungsam Tsangla is a regional dialect of the Tsangla language spoken primarily in the Dungsam area of eastern Bhutan.
  • D. Lhuentse
    Lhuentse is a small town in northeastern Bhutan known for its traditional Bhutanese architecture, rich cultural heritage, and production of fine handwoven textiles.
  • E. Rinchinbal
    Rinchinbal was a short-reigning 14th-century Mongol emperor of the Yuan dynasty in China, known for ascending the throne as a child.
  • 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_69e2458750b481908a8e4cf4609cc6cf completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17eb74700819090d191b3a7a17034 completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:36 p.m.