Triple
T25954280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Obelisk of Theodosius |
E654052
|
entity |
| Predicate | baseDecoration |
P2788
|
FINISHED |
| Object | reliefs depicting Theodosius I |
—
|
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: reliefs depicting Theodosius I | Statement: [Obelisk of Theodosius, baseDecoration, reliefs depicting Theodosius I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baseDecoration Context triple: [Obelisk of Theodosius, baseDecoration, reliefs depicting Theodosius I]
-
A.
setDecoration
Indicates assigning or updating a decorative property or appearance for a target entity or object.
-
B.
relatedDecoration
Indicates that one decoration is associated with, complements, or is contextually linked to another decoration.
-
C.
typeOfDecoration
chosen
Indicates the specific kind or style of decoration associated with an entity or applied in a given context.
-
D.
maskDecoration
Indicates that one entity serves as a decorative element or embellishment applied to a mask.
-
E.
decorationClass
Indicates that one entity serves as a decorative classification or style category applied to another entity.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 22, 2026, 8:44 a.m.