Triple

T21682073
Position Surface form Disambiguated ID Type / Status
Subject Tus, Iran E535132 entity
Predicate partOf P40 FINISHED
Object Greater Khorasan NE NERFINISHED

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: Greater Khorasan | Statement: [Tus, Iran, partOf, Greater Khorasan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greater Khorasan
Context triple: [Tus, Iran, partOf, Greater Khorasan]
  • A. Khorasan chosen
    Khorasan is a historical region in northeastern Iran and surrounding areas that served as a major cultural and political center in various Persian and Islamic empires.
  • B. Khurashan
    Khurashan was a Georgian noblewoman known primarily as the wife of King Levan of Kakheti in the 16th century.
  • C. Khorasan Province
    Khorasan Province was a large historical region and former administrative division in northeastern Iran, known for its cultural significance and strategic location along the Silk Road.
  • D. Dalir region
    The Dalir region is a rural area in western Iceland known for its scenic valleys, traditional farming communities, and historical ties to Icelandic sagas.
  • E. Registan
    Registan is a historic public square in Samarkand, Uzbekistan, famed for its stunning ensemble of Timurid-era madrasas adorned with intricate tilework and monumental architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c469b6ec8190aee4cadd1527db91 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef96c69990819088a1134ecea09099 completed April 27, 2026, 5:03 p.m.
Created at: April 16, 2026, 6:43 p.m.