Triple
T14805881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | suffes |
E348032
|
entity |
| Predicate | analogousToOffice |
P66071
|
FINISHED |
| Object | Roman consul |
—
|
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: Roman consul | Statement: [suffes, analogousToOffice, Roman consul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: analogousToOffice Context triple: [suffes, analogousToOffice, Roman consul]
-
A.
equivalentOffice
Indicates that two offices are considered functionally or formally the same position, role, or authority, even if they differ in name or jurisdiction.
-
B.
relatesToOffice
Indicates that one entity has a connection, association, or relevance to an office, its functions, or its environment.
-
C.
worksWithOffice
Indicates that an entity collaborates or is professionally associated with a particular office or office-based organization.
-
D.
comparableOffice
chosen
Indicates that two offices are sufficiently similar in relevant characteristics (such as size, function, or status) to be meaningfully compared to each other.
-
E.
usedOffice
Indicates that an entity made use of or occupied a particular office or workplace.
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decf32666081908e84f985c47eb963 |
completed | April 14, 2026, 11:35 p.m. |
| PD | Predicate disambiguation | batch_69de8c0ef8a4819092d84478b1f56db1 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:34 a.m.