Triple
T19055634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teatro dell'Opera di Roma |
E466385
|
entity |
| Predicate | hasDomeOrCeilingDecoration |
P34815
|
FINISHED |
| Object | ornate ceiling frescoes |
—
|
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: ornate ceiling frescoes | Statement: [Teatro dell'Opera di Roma, hasDomeOrCeilingDecoration, ornate ceiling frescoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDomeOrCeilingDecoration Context triple: [Teatro dell'Opera di Roma, hasDomeOrCeilingDecoration, ornate ceiling frescoes]
-
A.
hasDomeDecoration
Indicates that an entity’s dome is adorned with specific decorative elements or ornamentation.
-
B.
hasCeilingDecoration
chosen
Indicates that an entity features or is adorned with a decorative element on its ceiling.
-
C.
hasDomeDesign
Indicates that one entity features or incorporates the dome design of another entity.
-
D.
hasDomeStyle
Indicates that one entity (typically a building or structure) possesses a dome characterized by a particular architectural style or form.
-
E.
hasRichInteriorDecoration
Indicates that an entity features elaborate, ornate, or luxuriously detailed interior decoration.
- 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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5dc056b708190a2b84cbddf0fc2d9 |
completed | April 20, 2026, 7:55 a.m. |
| PD | Predicate disambiguation | batch_69e4b99633c8819097988608c278ecf8 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:03 p.m.