Triple

T2220854
Position Surface form Disambiguated ID Type / Status
Subject Darius I of Persia E48135 entity
Predicate languageUsed P238 FINISHED
Object Elamite E83627 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: Elamite | Statement: [Darius I of Persia, languageUsed, Elamite]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elamite
Context triple: [Darius I of Persia, languageUsed, Elamite]
  • A. Elamite chosen
    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.
  • 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. Akkadian
    Akkadian is an extinct Semitic language of ancient Mesopotamia, historically used in Assyria and Babylonia and written in cuneiform script.
  • D. Akkad
    Akkad was an ancient Mesopotamian city and region best known as the center of the Akkadian Empire, one of the world’s earliest great empires.
  • E. Avestan language
    The Avestan language is an ancient Eastern Iranian language known primarily as the liturgical language of Zoroastrianism and the sacred texts of the Avesta.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0156c8c819083e3e3b6ede1e951 completed March 7, 2026, 6:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae655df21c8190aa9624f15955c565 completed March 9, 2026, 6:14 a.m.
Created at: March 4, 2026, 7:46 p.m.