Triple

T1223243
Position Surface form Disambiguated ID Type / Status
Subject Maurya Empire E26270 entity
Predicate script P505 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: [Maurya Empire, script, Kharosthi script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kharosthi script
Context triple: [Maurya Empire, script, 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. Nagari script
    Nagari script is an early North Indian writing system that evolved into later scripts such as Devanagari and was used historically for writing Sanskrit and related languages.
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be233fd88190996faf4105c0b8d7 completed March 1, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e5dd8148190a209257ee29969dd completed March 8, 2026, 5:51 a.m.
Created at: March 1, 2026, 7:47 p.m.