Triple

T10816937
Position Surface form Disambiguated ID Type / Status
Subject Erfurt manuscript E255255 entity
Predicate instanceOf P0 FINISHED
Object medieval Hebrew manuscript C28376 CONCEPT FINISHED

How this triple was built (1 step)

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.

CD Concept disambiguation gpt-5-mini-2025-08-07
Target class: medieval Hebrew manuscript
Context triple: [Erfurt manuscript, instanceOf, medieval Hebrew manuscript]
  • A. medieval Hebrew lexicographical work
    A medieval Hebrew lexicographical work is a scholarly text from the Middle Ages that systematically defines, explains, and often translates Hebrew words, typically for biblical, liturgical, or grammatical study.
  • B. Gothic manuscript
    A Gothic manuscript is a handwritten book or document produced in medieval Europe, characterized by dense, angular Gothic script, elaborate illumination, and often religious or legal content.
  • C. late antique manuscript
    A late antique manuscript is a handwritten document produced between roughly the 3rd and 8th centuries CE, typically on papyrus or parchment, reflecting the transitional cultural, religious, and artistic practices of the late Roman and early medieval worlds.
  • D. Insular manuscript
    An Insular manuscript is a handwritten book produced in the British Isles between the 7th and 9th centuries, characterized by distinctive Hiberno-Saxon script, intricate interlace ornament, and elaborate decorated initials.
  • E. Glagolitic manuscript
    A Glagolitic manuscript is a handwritten document produced using the Glagolitic alphabet, one of the earliest Slavic scripts, typically preserving religious, liturgical, or legal texts from the medieval Slavic cultural sphere.
  • F. None of above. chosen

Provenance (1 batch)

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_69d6aa8081448190a9324184f2bd1c26 completed April 8, 2026, 7:20 p.m.
Created at: April 8, 2026, 9:18 p.m.