Triple
T2001650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Saturn |
E43483
|
entity |
| Predicate | visibleRemains |
P35040
|
FINISHED |
| Object | eight columns with entablature |
—
|
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: eight columns with entablature | Statement: [Temple of Saturn, visibleRemains, eight columns with entablature]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visibleRemains Context triple: [Temple of Saturn, visibleRemains, eight columns with entablature]
-
A.
visibleAt
Indicates that one entity can be seen or perceived from a specific location, viewpoint, or context at a given time.
-
B.
visibilityDuration
Indicates the length of time for which something remains visible or observable.
-
C.
visibleAtSurface
Indicates that something can be seen or is observable at the outer surface of an object or medium.
-
D.
covered
Indicates that one entity lies over or on top of another entity so as to conceal, protect, or obscure it.
-
E.
visibilityRequirement
Indicates that one entity must be visible or perceivable under specified conditions for another entity, action, or rule to apply.
- F. None of above. chosen
Provenance (4 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_69a88715dbbc8190b2299e29e955d997 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb880c710819098fb877052ce56dc |
completed | March 7, 2026, 5:32 a.m. |
| PD | Predicate disambiguation | batch_69abb79e63c08190982c8b44a557266f |
completed | March 7, 2026, 5:29 a.m. |
| PDg | Predicate description generation | batch_69abb87b9fc08190a748c278ef2d7dc7 |
completed | March 7, 2026, 5:32 a.m. |
Created at: March 4, 2026, 7:37 p.m.