Triple

T9561552
Position Surface form Disambiguated ID Type / Status
Subject Shughni E230685 entity
Predicate hasDialect P4251 FINISHED
Object Roshani
Roshani is a regional dialect of the Shughni language spoken by communities in the Pamir region of Central Asia.
E806536 NE FINISHED

How this triple was built (4 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: Roshani | Statement: [Shughni, hasDialect, Roshani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roshani
Context triple: [Shughni, hasDialect, Roshani]
  • A. Shiva Rose
    Shiva Rose is an American actress, blogger, and holistic lifestyle advocate known for her work in film and television as well as her natural beauty and wellness brand.
  • B. Roshini
    Roshini is an Indian actress known for her work in Tamil cinema and for being the sister of popular actress Jyothika.
  • C. Shantanava
    Shantanava is an epithet of Bhishma, the revered grandsire and formidable warrior of the Mahabharata, known for his vow of lifelong celibacy and unwavering loyalty to the Kuru throne.
  • D. Parushni
    Parushni is the ancient Vedic name for the Ravi River, one of the major rivers of the northwestern Indian subcontinent.
  • E. Anika
    Anika is the first name of Anika Noni Rose, an American actress and singer best known for voicing Tiana in Disney’s "The Princess and the Frog."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Roshani
Triple: [Shughni, hasDialect, Roshani]
Generated description
Roshani is a regional dialect of the Shughni language spoken by communities in the Pamir region of Central Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roshani
Target entity description: Roshani is a regional dialect of the Shughni language spoken by communities in the Pamir region of Central Asia.
  • A. Shiva Rose
    Shiva Rose is an American actress, blogger, and holistic lifestyle advocate known for her work in film and television as well as her natural beauty and wellness brand.
  • B. Roshini
    Roshini is an Indian actress known for her work in Tamil cinema and for being the sister of popular actress Jyothika.
  • C. Shantanava
    Shantanava is an epithet of Bhishma, the revered grandsire and formidable warrior of the Mahabharata, known for his vow of lifelong celibacy and unwavering loyalty to the Kuru throne.
  • D. Parushni
    Parushni is the ancient Vedic name for the Ravi River, one of the major rivers of the northwestern Indian subcontinent.
  • E. Anika
    Anika is the first name of Anika Noni Rose, an American actress and singer best known for voicing Tiana in Disney’s "The Princess and the Frog."
  • F. None of above. chosen

Provenance (5 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_69ca847e53a88190a60eed7e02257f10 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd994d31e08190b139f5ad10d8ea31 completed April 1, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69d152a014a48190925d52967e1fbffe completed April 4, 2026, 6:04 p.m.
NEDg Description generation batch_69d1539bad8481909f9bd060aa3b651c completed April 4, 2026, 6:08 p.m.
NED2 Entity disambiguation (via description) batch_69d154567f408190a848eea4ca905fb6 completed April 4, 2026, 6:11 p.m.
Created at: March 30, 2026, 8:03 p.m.