Triple
T8448818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rotunda of Galerius in Thessalonica |
E199748
|
entity |
| Predicate | conversionToChurchDate |
P46584
|
FINISHED |
| Object | late 4th century |
—
|
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: late 4th century | Statement: [Rotunda of Galerius in Thessalonica, conversionToChurchDate, late 4th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conversionToChurchDate Context triple: [Rotunda of Galerius in Thessalonica, conversionToChurchDate, late 4th century]
-
A.
conversionToMosqueDate
Indicates the date on which a building or site was converted into a mosque.
-
B.
dateInEasternOrthodoxChurches
Indicates that the specified date is observed or used according to the liturgical calendar of Eastern Orthodox churches.
-
C.
dateInAnglicanCommunion
Indicates that a given date is recognized and observed within the liturgical calendar of the Anglican Communion.
-
D.
convertedToChurch
chosen
Indicates that something has been transformed or repurposed into a church.
-
E.
dateInRomanCatholicChurch
Indicates that a specific date is recognized, observed, or used within the context of the Roman Catholic Church’s liturgical or ecclesiastical calendar.
- 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_69ca83170f9081909cd98f55614c6476 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe445b7988190b53ae45070c70d1d |
completed | March 31, 2026, 3:12 p.m. |
| PD | Predicate disambiguation | batch_69cbd0f5a3648190beb53a139a2d5482 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:09 p.m.