Triple
T21576338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman provincial administration |
E532402
|
entity |
| Predicate | reliesOnOffice |
P86596
|
FINISHED |
| Object | proconsul |
—
|
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: proconsul | Statement: [Roman provincial administration, reliesOnOffice, proconsul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reliesOnOffice Context triple: [Roman provincial administration, reliesOnOffice, proconsul]
-
A.
relatesToOffice
Indicates that one entity has a connection, association, or relevance to an office, its functions, or its environment.
-
B.
supportsOffice
Indicates that one entity provides assistance, resources, or endorsement to an office or officeholder in performing its functions or maintaining its operations.
-
C.
requiresConcurrentOffice
chosen
Indicates that one entity’s validity, operation, or status depends on another entity holding a specific office or position at the same time.
-
D.
requiresOffice
Indicates that performing or fulfilling the related activity, role, or condition depends on being in or having access to a physical office location.
-
E.
usedByOffice
Indicates that something is utilized, operated, or employed by an office or office-related entity.
- 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_69e0c4618bec8190bcb0feb74568cbb1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9d07ddc8190a4bba08223e56f46 |
completed | April 27, 2026, 4:45 a.m. |
| PD | Predicate disambiguation | batch_69e6320c8c2c81908bf031447d66a052 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:31 p.m.