Triple
T31065078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anicia Juliana |
E791643
|
entity |
| Predicate | timeOfViennaDioscuridesCommission |
P185651
|
FINISHED |
| Object | circa 512 |
—
|
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: circa 512 | Statement: [Anicia Juliana, timeOfViennaDioscuridesCommission, circa 512]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfViennaDioscuridesCommission Context triple: [Anicia Juliana, timeOfViennaDioscuridesCommission, circa 512]
-
A.
placeOfViennaDioscuridesProduction
Indicates the location where the Vienna Dioscurides manuscript was produced.
-
B.
endTime (Council of Vienne)
Indicates the point in time at which the Council of Vienne concluded or formally ended.
-
C.
timeOfCodification
Indicates the specific point in time at which something (such as a rule, law, or concept) was formally codified or recorded.
-
D.
officeStartTime (Mayor of Vienna)
Indicates the time at which the Mayor of Vienna officially begins their term in office.
-
E.
EuropeanRediscoveryDate
Indicates the date on which a place, object, or phenomenon was first documented or encountered by Europeans after having been previously unknown or forgotten in European records.
- 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_69f224cc0c5c81908404f087bff92997 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7c33d59808190b647989a093f3488 |
completed | May 3, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b6e7a881908deb96bedb2713f4 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c29cf36481908e472d4dcb5573b9 |
completed | May 3, 2026, 9:48 p.m. |
Created at: April 29, 2026, 9:01 p.m.