Triple

T6136485
Position Surface form Disambiguated ID Type / Status
Subject Behistun Inscription E136845 entity
Predicate language P15 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: [Behistun Inscription, language, Elamite]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elamite
Context triple: [Behistun Inscription, language, 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. Elam
    Elam was an ancient civilization in what is now southwestern Iran, known for its early urban culture, distinctive language, and long-standing interactions and conflicts with Mesopotamian states.
  • C. Elamite cuneiform
    Elamite cuneiform is an ancient script adapted from Mesopotamian cuneiform and used to write the Elamite language in what is now southwestern Iran.
  • D. Linear Elamite
    Linear Elamite is an ancient script used in southwestern Iran during the late 3rd to early 2nd millennium BCE to write the Elamite language.
  • E. 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.
  • 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_69c008a179388190a3b5a081bbf46d55 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c8211d48190bc10675ba6707150 completed March 22, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135e22b9481908e6023d1b0a5d0fd completed March 23, 2026, 12:45 p.m.
Created at: March 22, 2026, 4:15 p.m.