Triple

T15583188
Position Surface form Disambiguated ID Type / Status
Subject Romanos II E374549 entity
Predicate ethnicity P194 FINISHED
Object Byzantine Greek E5872 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: Byzantine Greek | Statement: [Romanos II, ethnicity, Byzantine Greek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Byzantine Greek
Context triple: [Romanos II, ethnicity, Byzantine Greek]
  • A. Cappadocian Greek
    Cappadocian Greek is an endangered Greek dialect historically spoken in the Cappadocia region of central Anatolia, notable for its heavy influence from Turkish and preservation of archaic Greek features.
  • B. Romaniote Greek
    Romaniote Greek is the historical Greek dialect traditionally spoken by the Romaniote Jews of the Eastern Mediterranean, especially in Greece.
  • C. Arcadocypriot Greek
    Arcadocypriot Greek is an ancient dialect of the Greek language historically spoken in parts of Arcadia on the Peloponnese and on the island of Cyprus.
  • D. Koine Greek
    Koine Greek is the common dialect of ancient Greek that served as the primary language of the New Testament and early Christian writings.
  • E. Medieval Greek chosen
    Medieval Greek is the historical stage of the Greek language used from roughly the 6th to the 15th century, bridging Ancient/Koine Greek and Modern Greek and serving as the linguistic medium of the Byzantine Empire.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e47971481909e986dd999354628 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4f71e48190a15eb0a2138f083f completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:11 a.m.