Triple
T16914810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portonaccio sanctuary |
E410293
|
entity |
| Predicate | roofDecorationType |
P61388
|
FINISHED |
| Object | polychrome terracotta decoration |
—
|
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: polychrome terracotta decoration | Statement: [Portonaccio sanctuary, roofDecorationType, polychrome terracotta decoration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofDecorationType Context triple: [Portonaccio sanctuary, roofDecorationType, polychrome terracotta decoration]
-
A.
roofFeature
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
-
B.
hasCeilingDecoration
Indicates that an entity features or is adorned with a decorative element on its ceiling.
-
C.
hasDomeDecoration
Indicates that an entity’s dome is adorned with specific decorative elements or ornamentation.
-
D.
decoration
Indicates that one entity serves as an ornament or embellishing element for another entity, enhancing its appearance or style.
-
E.
decorativeFinish
chosen
Indicates that one entity serves as an ornamental or aesthetic surface treatment 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3ca4015648190989904ad7119c3be |
completed | April 18, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69e32b9489408190bcb2ede567ff5bf9 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.