Triple

T5488312
Position Surface form Disambiguated ID Type / Status
Subject Saka E123639 entity
Predicate writingSystem P454 FINISHED
Object Kharosthi script E125350 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: Kharosthi script | Statement: [Saka, writingSystem, Kharosthi script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kharosthi script
Context triple: [Saka, writingSystem, Kharosthi script]
  • A. Kharoṣṭhī script chosen
    The Kharoṣṭhī script is an ancient right-to-left writing system used in northwestern South Asia, especially in the Gandhāra region, primarily for early Buddhist and administrative texts.
  • B. Prachalit script
    Prachalit script is a historical Brahmic writing system used primarily for the Nepal Bhasa (Newar) language of the Kathmandu Valley.
  • C. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • D. 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.
  • E. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • 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_69bd464a2d908190869324ce176779c8 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd9264d014819097c83bb5c2bb8c39 completed March 20, 2026, 6:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf8bc7fd6481908ec09b2ef68addba completed March 22, 2026, 6:27 a.m.
Created at: March 20, 2026, 2:10 p.m.