Triple

T2495455
Position Surface form Disambiguated ID Type / Status
Subject Kushan Empire E52143 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: [Kushan Empire, writingSystem, Kharosthi script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kharosthi script
Context triple: [Kushan Empire, 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. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • C. 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.
  • D. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • E. Indus script
    The Indus script is an undeciphered system of symbols used by the ancient Indus Valley Civilization, known from short inscriptions on seals, tablets, and pottery dating to around 2600–1900 BCE.
  • 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_69ab4955111c8190835bf619adec21ff completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd19541048190b9e39db119c20fe8 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f9608e48190825417943e8c4559 completed March 9, 2026, 7:29 p.m.
Created at: March 6, 2026, 9:45 p.m.