Triple

T16071429
Position Surface form Disambiguated ID Type / Status
Subject Turfan manuscripts E389871 entity
Predicate hasScript P182 FINISHED
Object Sogdian script E168919 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: Sogdian script | Statement: [Turfan manuscripts, hasScript, Sogdian script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sogdian script
Context triple: [Turfan manuscripts, hasScript, Sogdian script]
  • A. Sogdian alphabet chosen
    The Sogdian alphabet is an ancient Middle Iranian script used by the Sogdian people of Central Asia, notable for its role in transmitting religious and commercial texts along the Silk Road and for influencing later writing systems such as the Old Uyghur and Mongolian scripts.
  • 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. Parthian script
    Parthian script is an ancient Middle Iranian writing system used primarily for the Parthian language of the Parthian Empire, derived from the Aramaic script and influential on later Central Asian scripts.
  • D. Kharoṣṭhī script
    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.
  • E. Avestan script
    The Avestan script is an ancient writing system developed to record the sacred Zoroastrian texts in the Avestan language and related early Iranian 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183be909c8190ac6c37ab047151ae completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe4827cd48190aa470c6537e72508 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:57 a.m.