Triple
T8896218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codex Ephraemi Rescriptus |
E211810
|
entity |
| Predicate | palimpsestOvertextContent |
P39049
|
FINISHED |
| Object | Greek translations of sermons of Ephraem the Syrian |
—
|
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: Greek translations of sermons of Ephraem the Syrian | Statement: [Codex Ephraemi Rescriptus, palimpsestOvertextContent, Greek translations of sermons of Ephraem the Syrian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: palimpsestOvertextContent Context triple: [Codex Ephraemi Rescriptus, palimpsestOvertextContent, Greek translations of sermons of Ephraem the Syrian]
-
A.
palimpsest
Indicates that something has been reused or overwritten while still retaining traces or remnants of its earlier form or content.
-
B.
textContent
chosen
Indicates that one entity is the textual content or written material contained within another entity.
-
C.
coverText
Indicates that one text serves as the cover or front-facing textual representation for another work or resource.
-
D.
parchmentColor
Indicates that one entity has the color characteristic of parchment in relation to another entity.
-
E.
textFragment
Indicates that one piece of text is a constituent part or segment of a larger text.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61bfec0881908e4ef5b7f0e6b542 |
completed | April 1, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2bfb38819083d5eb1af8ccf4d6 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:54 p.m.