Triple

T1770081
Position Surface form Disambiguated ID Type / Status
Subject Nagari script E38853 entity
Predicate hasAlternateName P39 FINISHED
Object Nāgarī script E6056 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: Nāgarī script | Statement: [Nagari script, hasAlternateName, Nāgarī script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nāgarī script
Context triple: [Nagari script, hasAlternateName, Nāgarī script]
  • A. Brahmi script
    The Brahmi script is one of the oldest writing systems of the Indian subcontinent, serving as the ancestor of most modern South and Southeast Asian scripts.
  • B. Devanagari script chosen
    Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
  • C. Nandinagari script
    Nandinagari script is a historical Brahmic script of southern India, primarily used to write Sanskrit and related languages in the Deccan region.
  • D. Gupta script
    The Gupta script is an ancient Brahmi-derived writing system of India that served as a key ancestor to many later South Asian scripts, including those used for Sanskrit and regional languages.
  • E. Grantha script
    Grantha script is a historical South Indian writing system primarily used to record Sanskrit texts, especially in the Tamil-speaking regions.
  • 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_69a8862e61708190af97b9838cc3f5de completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa648eb9488190b1be2d2b6d259634 completed March 6, 2026, 5:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae1fc02b948190bc28175ff8c46110 completed March 9, 2026, 1:17 a.m.
Created at: March 4, 2026, 7:31 p.m.