Triple
T6018696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codex Marianus |
E134009
|
entity |
| Predicate | scriptColor |
P60
|
FINISHED |
| Object | brown ink |
—
|
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: brown ink | Statement: [Codex Marianus, scriptColor, brown ink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptColor Context triple: [Codex Marianus, scriptColor, brown ink]
-
A.
scriptStyle
Indicates that one entity specifies or characterizes the stylistic form or manner of a script associated with another entity.
-
B.
signatureColor
Indicates that an entity has a characteristic or defining color that is uniquely or primarily associated with it.
-
C.
pasteColor
Indicates that one entity applies or transfers a color from a source to a target, effectively pasting that color onto the target.
-
D.
colors
chosen
Indicates that one entity assigns, describes, or provides the color or colors of another entity.
-
E.
script
Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
- 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_69c008742a5c8190b9cb9c2787a3d8b3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f8589d0819089ae7840461640f6 |
completed | March 22, 2026, 8:22 p.m. |
| PD | Predicate disambiguation | batch_69c049e75b3881908be106fbcf8c68d4 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:07 p.m.