Triple

T20067112
Position Surface form Disambiguated ID Type / Status
Subject Arya E499635 entity
Predicate usedInLanguage P907 FINISHED
Object Avestan 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: Avestan | Statement: [Arya, usedInLanguage, Avestan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Avestan
Context triple: [Arya, usedInLanguage, Avestan]
  • A. Avestan language chosen
    The Avestan language is an ancient Eastern Iranian language known primarily as the liturgical language of Zoroastrianism and the sacred texts of the Avesta.
  • B. Old Persian
    Old Persian is an ancient Iranian language used in the Achaemenid Empire, primarily known from royal inscriptions such as those of Darius the Great.
  • C. Iranun language
    The Iranun language is an Austronesian language spoken by the Iranun people of the southern Philippines and parts of Sabah and Mindanao, closely related to Maranao and Maguindanaon.
  • D. Elamite
    Elamite is an ancient language of southwestern Iran, historically used in the kingdom of Elam and later as an administrative language under the Achaemenid Empire.
  • E. Old Iranian languages
    Old Iranian languages are the earliest attested branch of the Iranian language family, including ancient tongues such as Avestan and Old Persian used in early Iranian civilizations.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66379f2cc81908f13a7b216878f12 completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:39 p.m.