Triple
T2376725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pannonia |
E46213
|
entity |
| Predicate | typeOfGovernor |
P1893
|
FINISHED |
| Object | legatus Augusti pro praetore |
—
|
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: legatus Augusti pro praetore | Statement: [Pannonia, typeOfGovernor, legatus Augusti pro praetore]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfGovernor Context triple: [Pannonia, typeOfGovernor, legatus Augusti pro praetore]
-
A.
governorateType
Indicates the specific classification or category of a governorate within an administrative or governmental hierarchy.
-
B.
governorTitle
chosen
Indicates the official title or designation held by a person serving as a governor.
-
C.
governorateOf
Indicates that one entity is the governorate (administrative region) to which another entity belongs or is located within.
-
D.
currentGovernor
Indicates that one entity is the person who presently holds the office of governor of the other entity.
-
E.
governmentType
Indicates the form or system of governance under which an entity (such as a country or organization) is organized and ruled.
- 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_69a88a1554a48190a0180682bcf099be |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abca4d89248190be7d712d5fa8382b |
completed | March 7, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69abc59d82f08190b7c36982d1ae783d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.