Triple
T17279588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ponte dei Quattro Capi |
E419486
|
entity |
| Predicate | hasSpandrelDecor |
P38145
|
FINISHED |
| Object | four-headed herms |
—
|
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: four-headed herms | Statement: [Ponte dei Quattro Capi, hasSpandrelDecor, four-headed herms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpandrelDecor Context triple: [Ponte dei Quattro Capi, hasSpandrelDecor, four-headed herms]
-
A.
hasSpandrel
Indicates a structural relationship where one element includes or is connected to a spandrel, typically as the space or panel between two architectural supports or openings.
-
B.
hasDecor
chosen
Indicates that one entity possesses, features, or is adorned with a particular decorative element or style.
-
C.
hasChapelDecoration
Indicates that a chapel possesses or features a particular decorative element or ornamentation.
-
D.
hasCeilingDecoration
Indicates that an entity features or is adorned with a decorative element on its ceiling.
-
E.
hasDomeDecoration
Indicates that an entity’s dome is adorned with specific decorative elements or ornamentation.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e433286f6c8190bf4a757707707e22 |
completed | April 19, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69e3832c3b98819091967ac7e91ba316 |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:40 a.m.