Triple

T22321581
Position Surface form Disambiguated ID Type / Status
Subject Beylik of Aydın E551799 entity
Predicate currency P245 FINISHED
Object Akçe 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: Akçe | Statement: [Beylik of Aydın, currency, Akçe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akçe
Context triple: [Beylik of Aydın, currency, Akçe]
  • A. Akçe chosen
    Akçe was the primary silver coin and monetary unit of the Ottoman Empire for several centuries, widely used across its territories.
  • B. Akassa
    Akassa is a dialect of the Nembe language spoken by communities in the Niger Delta region of Nigeria.
  • C. Akçura
    Akçura is a Turkish surname most notably associated with Yusuf Akçura, an influential early 20th-century intellectual and proponent of Turkish nationalism.
  • D. Dinar
    Dinar is a town and district in Turkey known as a regional hub in Afyonkarahisar Province, situated near the sources of the Büyük Menderes River.
  • E. Dinar
    The Dinar is a historic gold coin and monetary unit widely used across the Islamic world, originating as the standard currency of early Muslim empires.
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15764d3a48190af79ce4642b7f563 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.