Triple

T5687558
Position Surface form Disambiguated ID Type / Status
Subject Loulan E125348 entity
Predicate hasLanguageEvidence P14924 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: [Loulan, hasLanguageEvidence, Kharosthi script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kharosthi script
Context triple: [Loulan, hasLanguageEvidence, 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. Bactrian script
    Bactrian script is an ancient writing system derived from the Greek alphabet that was used to write the Bactrian language in Central Asia.
  • C. Prachalit script
    Prachalit script is a historical Brahmic writing system used primarily for the Nepal Bhasa (Newar) language of the Kathmandu Valley.
  • D. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • E. 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.
  • 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_69c0082a884c8190a79001bae658941f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023be18a081908c72fb5b0e1852f9 completed March 22, 2026, 5:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a43cce88190b8ac801018f05561 completed March 22, 2026, 9:08 p.m.
Created at: March 22, 2026, 3:44 p.m.