Triple
T25994683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dresden Codex |
E646451
|
entity |
| Predicate | containsDeityDepictions |
P86688
|
FINISHED |
| Object | Chaac |
—
|
NE NERFINISHED |
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: Chaac | Statement: [Dresden Codex, containsDeityDepictions, Chaac]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsDeityDepictions Context triple: [Dresden Codex, containsDeityDepictions, Chaac]
-
A.
depictedWithDeity
Indicates that an entity is shown or represented together with a particular deity in some form of depiction.
-
B.
depictedDeity
chosen
Indicates that one entity is a deity who is shown or represented in an image, artwork, or visual depiction associated with another entity.
-
C.
portraysDeity
Indicates that one entity represents, depicts, or characterizes another entity as a deity or divine being.
-
D.
hasAllegoricalDepictionsBy
Indicates that one entity is represented through allegorical depictions created by another entity.
-
E.
hasDeity
Indicates that one entity recognizes, worships, or is associated with another entity as its deity or divine figure.
- 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_69e77e88cb8481908da31d4a00661f55 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f7431c0eec81909ead443e07d75e18 |
completed | May 3, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69f74143cf708190a12d487884298437 |
completed | May 3, 2026, 12:36 p.m. |
Created at: April 22, 2026, 8:57 a.m.