Triple
T30107889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codex Ephraemi Rescriptus |
E765180
|
entity |
| Predicate | palimpsestType |
P85110
|
FINISHED |
| Object | biblical text under patristic text |
—
|
LITERAL 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: biblical text under patristic text | Statement: [Codex Ephraemi Rescriptus, palimpsestType, biblical text under patristic text]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: palimpsestType Context triple: [Codex Ephraemi Rescriptus, palimpsestType, biblical text under patristic text]
-
A.
palimpsest
Indicates that something has been reused or overwritten while still retaining traces or remnants of its earlier form or content.
-
B.
palimpsestUpperText
chosen
Indicates that one text is written over and partially obscures an earlier erased text on the same writing surface.
-
C.
palimpsestOvertextLanguage
Indicates the language in which the overlying (later-added) text of a palimpsest is written.
-
D.
palimpsestOvertextAuthor
Indicates that an author is responsible for writing the overlying (later) text layer in a palimpsest.
-
E.
epigraphicType
Indicates the specific kind or category of an inscription as classified in epigraphic studies.
- F. None of above.
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_69f22475ad7c8190be7f9541044a0bbb |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67dbc4278819088f599a06c490287 |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:09 p.m.