Triple
T10538231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Divus Romulus |
E248626
|
entity |
| Predicate | hasSpolia |
P37681
|
FINISHED |
| Object | reused architectural elements in later periods |
—
|
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: reused architectural elements in later periods | Statement: [Temple of Divus Romulus, hasSpolia, reused architectural elements in later periods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpolia Context triple: [Temple of Divus Romulus, hasSpolia, reused architectural elements in later periods]
-
A.
usesSpoliaFrom
chosen
Indicates that one entity incorporates or reuses building materials, decorative elements, or structural components taken from another, earlier structure or object.
-
B.
lootedBy
Indicates that something has been forcibly taken or plundered by a specified agent or group.
-
C.
hadEstate
Indicates that an entity possessed or owned a particular estate or landed property.
-
D.
hasColossiOf
Indicates that one entity possesses, contains, or is characterized by monumental statues or colossal figures associated with another entity.
-
E.
hasRuin
Indicates that one entity possesses, contains, or is associated with a ruin or ruined structure.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a56133c819088285522e64831f7 |
completed | April 7, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69d4fb9729288190a0149f127acd7ae3 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:31 p.m.