Triple

T21908449
Position Surface form Disambiguated ID Type / Status
Subject Lepcha E541000 entity
Predicate nativeTo P410 FINISHED
Object Sikkim region 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: Sikkim region | Statement: [Lepcha, nativeTo, Sikkim region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sikkim region
Context triple: [Lepcha, nativeTo, Sikkim region]
  • A. Sikkim chosen
    Sikkim is a small, mountainous Indian state in the eastern Himalayas known for its dramatic landscapes, Buddhist monasteries, and proximity to Mount Kanchenjunga.
  • B. Seemanchal
    Seemanchal is a region in the northeastern part of Bihar, India, known for its dense population, agrarian economy, and socio-economic underdevelopment.
  • C. Meghalayan
    The Meghalayan is the most recent and current age of the Holocene epoch, defined by a global climatic event marked by a major drought and cooling period that began about 4,200 years ago.
  • D. Darjeeling Himalayan region
    The Darjeeling Himalayan region is a mountainous area in the eastern Himalayas of India, renowned for its tea plantations, scenic landscapes, and views of Kanchenjunga.
  • E. Sikkim Himalaya
    Sikkim Himalaya is a mountainous region in northeastern India known for its high peaks, including Kanchenjunga, rich biodiversity, and distinctive Himalayan culture.
  • 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_69e0c47b4e8c81908c8076eaa4c8e4f2 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f121d806688190b23502aacbfde4bd completed April 28, 2026, 9:08 p.m.
Created at: April 16, 2026, 7:39 p.m.