Triple

T1023208
Position Surface form Disambiguated ID Type / Status
Subject Gandhari Prakrit E22083 entity
Predicate associatedScript P16423 FINISHED
Object Kharoṣṭhī E125350 NE FINISHED

How this triple was built (3 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: Kharoṣṭhī | Statement: [Gandhari Prakrit, associatedScript, Kharoṣṭhī]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kharoṣṭhī
Context triple: [Gandhari Prakrit, associatedScript, Kharoṣṭhī]
  • 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. 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.
  • C. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • 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.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedScript
Context triple: [Gandhari Prakrit, associatedScript, Kharoṣṭhī]
  • A. relatedToScript chosen
    Indicates a general association or connection between an entity and a script, without specifying the exact nature of that relationship.
  • B. containsScript
    Indicates that one entity includes or embeds the script of another entity within it.
  • C. primaryScript
    Indicates the writing system or script that is chiefly used to represent the language or content of an entity.
  • D. script
    Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
  • E. officialScriptOf
    Indicates that one writing system is formally designated as the standard or legally recognized script used for a particular language, region, or entity.
  • F. None of above.

Provenance (4 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_69a493d6e380819097b384986ffc315c completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7e0f8908190bfe0a4cd8b31dfed completed March 1, 2026, 10:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac763582c48190bcf038162a1dea1c completed March 7, 2026, 7:02 p.m.
PD Predicate disambiguation batch_69a4b72619cc8190932fdfa0c74dc055 completed March 1, 2026, 10:01 p.m.
Created at: March 1, 2026, 7:41 p.m.