Triple
T13552737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silvio Berlusconi |
E323689
|
entity |
| Predicate | bannedFromOffice |
P22057
|
FINISHED |
| Object | Italian public office |
—
|
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: Italian public office | Statement: [Silvio Berlusconi, bannedFromOffice, Italian public office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bannedFromOffice Context triple: [Silvio Berlusconi, bannedFromOffice, Italian public office]
-
A.
wasBannedPartyLeader
Indicates that an individual was prohibited from serving as the leader of a political party, typically by an authority or legal restriction.
-
B.
methodOfRemovalFromOffice
Indicates the specific process or procedure by which an officeholder is removed from their position.
-
C.
excludedFromPoliticalRights
chosen
Indicates that an entity is denied or deprived of participation in political rights, such as voting, holding office, or engaging in formal political decision-making.
-
D.
bannedOppositionParties
Indicates that a governing authority has prohibited opposition political parties from operating or participating in the political process.
-
E.
officeHoldersMustNot
Indicates that certain individuals are prohibited from holding specified offices or positions.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbb9ee3f081909056dc1a92c40b7a |
completed | April 12, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69dbae13bec4819084c1770638c00ed9 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:46 p.m.