Triple
T9463333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Lorenzo in Miranda |
E228203
|
entity |
| Predicate | isBuiltOnTopOf |
P13359
|
FINISHED |
| Object | pagan temple site |
—
|
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: pagan temple site | Statement: [San Lorenzo in Miranda, isBuiltOnTopOf, pagan temple site]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBuiltOnTopOf Context triple: [San Lorenzo in Miranda, isBuiltOnTopOf, pagan temple site]
-
A.
hasTopConstruction
Indicates that one entity serves as the uppermost structural element or construction positioned on top of another entity.
-
B.
isToppedWith
Indicates that one entity serves as a topping placed on the surface of another entity.
-
C.
sitsAtop
chosen
Indicates that one entity is positioned directly on top of another, typically resting upon its upper surface.
-
D.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
E.
isStackedWith
Indicates that one object is positioned directly on top of or beneath another object so that they form a vertical stack together.
- 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_69ca846fee388190a6ec273fd644b88b |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7fcd9794819093c392489d4efbe9 |
completed | April 1, 2026, 8:27 p.m. |
| PD | Predicate disambiguation | batch_69cca55caaa8819089c5138e014892d3 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:53 p.m.