Triple
T3120314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codex Bezae |
E65167
|
entity |
| Predicate | hasColumnLayout |
P10827
|
FINISHED |
| Object | single column per page |
—
|
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: single column per page | Statement: [Codex Bezae, hasColumnLayout, single column per page]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColumnLayout Context triple: [Codex Bezae, hasColumnLayout, single column per page]
-
A.
hasColumns
Indicates that one entity possesses or is characterized by a set of columns associated with it.
-
B.
hasLayout
chosen
Indicates that one entity defines or is associated with the structural arrangement or organization (layout) of another entity.
-
C.
hasColumnCountBack
Indicates that an entity (such as a table or layout) has a specified number of columns on its back side or rear-facing section.
-
D.
hasColumnOrder
Indicates that one column in a sequence is positioned before or after another column, specifying their relative ordering.
-
E.
hasFrontColumns
Indicates that one entity possesses or features columns located at its front side.
- 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_69ad857fcc088190b0c4d45a5cde6f61 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada4eb6a6081909df41f67999eb4ff |
completed | March 8, 2026, 4:33 p.m. |
| PD | Predicate disambiguation | batch_69ad9df455088190940ad04419772dc8 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:04 p.m.