Triple

T6473173
Position Surface form Disambiguated ID Type / Status
Subject Marwaris E146004 entity
Predicate diaspora P2103 FINISHED
Object Nepal E15177 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: Nepal | Statement: [Marwaris, diaspora, Nepal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nepal
Context triple: [Marwaris, diaspora, Nepal]
  • A. Nepal chosen
    Nepal is a landlocked South Asian country in the Himalayas, known for Mount Everest, its rich cultural heritage, and its location between India and China.
  • B. Bhutan
    Bhutan is a small, landlocked Himalayan kingdom in South Asia known for its Buddhist culture, mountainous landscapes, and emphasis on Gross National Happiness.
  • C. Kingdom of Nepal
    The Kingdom of Nepal was a former Himalayan monarchy in South Asia, centered on the Kathmandu Valley, that existed until it became the Federal Democratic Republic of Nepal in 2008.
  • D. Naipali
    Naipali is an alternative name for Khas Kura, the historical Indo-Aryan language variety that evolved into modern standard Nepali.
  • E. Myanmar
    Myanmar is a Southeast Asian nation bordered by India, China, and Thailand, known for its diverse ethnic groups, Buddhist heritage, and long history of military rule and political turmoil.
  • 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_69c008fec7408190af7b146dc63d9750 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c06a3188488190a1b7452ede91ba5e completed March 22, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c65fc86d0c8190a254126255a7af1b completed March 27, 2026, 10:45 a.m.
Created at: March 22, 2026, 4:50 p.m.