Triple

T21139217
Position Surface form Disambiguated ID Type / Status
Subject Islamic Iran E520885 entity
Predicate hasEthnicGroup P1898 FINISHED
Object Mazandaranis 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: Mazandaranis | Statement: [Islamic Iran, hasEthnicGroup, Mazandaranis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mazandaranis
Context triple: [Islamic Iran, hasEthnicGroup, Mazandaranis]
  • A. Mazanderani people chosen
    The Mazanderani people are an Iranian ethnic group native to the southern coast of the Caspian Sea, known for their distinct Mazanderani language and rich regional culture.
  • B. Bakhtiari
    Bakhtiari is a surname most prominently associated with David Bakhtiari, an American football offensive tackle in the NFL.
  • C. Mazandarani
    Mazandarani is an Iranian language spoken primarily in Iran’s Mazandaran province along the southern coast of the Caspian Sea.
  • D. Kermani
    Kermani is a Persian-origin surname borne by various notable individuals, including writers, scholars, and public figures of Iranian descent.
  • E. Azarbarzin
    Azarbarzin is a character from Persian epic tradition, known primarily as the son of the legendary hero Esfandiyar.
  • 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7235e389881908813909e05d1413a completed April 21, 2026, 7:12 a.m.
Created at: April 16, 2026, 2:57 p.m.