Triple
T8475738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codex Argenteus |
E200388
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | late antique manuscript |
C24468
|
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: late antique manuscript Context triple: [Codex Argenteus, instanceOf, late antique manuscript]
-
A.
ancient manuscripts
Ancient manuscripts are original handwritten documents from past civilizations, typically preserved on materials like papyrus, parchment, or early paper, that provide primary evidence of historical, religious, literary, or scientific thought.
-
B.
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.
-
C.
Old English manuscript
An Old English manuscript is a handwritten document from early medieval England, typically on parchment, preserving texts in the Old English language along with their contemporary script, ornamentation, and material features.
-
D.
Septuagint manuscript
A Septuagint manuscript is a handwritten copy of the ancient Greek translation of the Hebrew Bible (and related texts), produced and transmitted by scribes in antiquity and the medieval period.
-
E.
Old English poetry manuscript
An Old English poetry manuscript is a handwritten medieval document preserving poetic texts in the Old English language, often featuring alliterative verse, scribal annotations, and culturally significant themes from Anglo-Saxon England.
- 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_69ca831b17988190a1f3f3413d57b820 |
completed | March 30, 2026, 2:05 p.m. |
Created at: March 30, 2026, 6:12 p.m.