Triple
T38167495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flavius Bauto |
E953187
|
entity |
| Predicate | wasPraetorianPrefectOf |
P52602
|
FINISHED |
| Object | Gaul |
—
|
NE NERFINISHED |
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: Gaul | Statement: [Flavius Bauto, wasPraetorianPrefectOf, Gaul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasPraetorianPrefectOf Context triple: [Flavius Bauto, wasPraetorianPrefectOf, Gaul]
-
A.
praetorianPrefect
chosen
Indicates a relationship where a person holds or is associated with the office or role of praetorian prefect.
-
B.
successorAsPraetorianPrefect
Indicates that one individual assumed the office of Praetorian Prefect directly after another, serving as that predecessor’s successor in the role.
-
C.
praetorianPrefectOfGaulStart
Indicates the time at which someone begins serving as Praetorian Prefect of Gaul.
-
D.
praetorianPrefectOfGaulEnd
Indicates the time or event at which a person’s tenure as Praetorian Prefect of Gaul comes to an end.
-
E.
praetorianPrefectOfItalyStart
Indicates the starting time or event when an individual assumed the office of Praetorian Prefect of Italy.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.