Triple

T21139421
Position Surface form Disambiguated ID Type / Status
Subject Brugmann's law E520890 entity
Predicate hasExampleLanguage P7390 FINISHED
Object Old 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: Old Avestan | Statement: [Brugmann's law, hasExampleLanguage, Old Avestan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Avestan
Context triple: [Brugmann's law, hasExampleLanguage, Old 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. 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.
  • 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. Proto-Iranian language
    The Proto-Iranian language is the reconstructed prehistoric ancestor of all Iranian languages, from which branches like Southwestern Iranian (including Persian) later developed.
  • 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.