Triple

T21201548
Position Surface form Disambiguated ID Type / Status
Subject Roshani language E522465 entity
Predicate hasAlternativeName P39 FINISHED
Object Roshani-Rushani 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: Roshani-Rushani | Statement: [Roshani language, hasAlternativeName, Roshani-Rushani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roshani-Rushani
Context triple: [Roshani language, hasAlternativeName, Roshani-Rushani]
  • A. Roshani chosen
    Roshani is a regional dialect of the Shughni language spoken by communities in the Pamir region of Central Asia.
  • B. Rushani
    Rushani is an Eastern Iranian language spoken primarily in the Rushan region of Tajikistan and neighboring areas.
  • C. Parushni
    Parushni is the ancient Vedic name for the Ravi River, one of the major rivers of the northwestern Indian subcontinent.
  • D. Suyashas
    Suyashas is a figure from Indian tradition known primarily as the son of King Dasharatha Maurya.
  • E. Shivini
    Shivini is the Urartian sun god, often associated with light, justice, and royal authority in the ancient Kingdom of Urartu.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73431973c81908c8682d7808a9d13 completed April 21, 2026, 8:24 a.m.
Created at: April 16, 2026, 3:18 p.m.