Triple
T281722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | President of Italy |
E5366
|
entity |
| Predicate | impeachmentGrounds |
P9571
|
FINISHED |
| Object | high treason |
—
|
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: high treason | Statement: [President of Italy, impeachmentGrounds, high treason]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impeachmentGrounds Context triple: [President of Italy, impeachmentGrounds, high treason]
-
A.
impeached
Indicates that a formal charge of misconduct has been brought against a public official through an official legislative or judicial process.
-
B.
canImpeach
Indicates that one entity has the authority or power to formally impeach another entity.
-
C.
impeachmentRole
Indicates the specific role or capacity an entity holds in relation to an impeachment process or proceeding.
-
D.
impeachmentConvictionThreshold
Indicates the required level of support or number of votes needed to convict an official in an impeachment proceeding.
-
E.
incumbentBlamedFor
Indicates that responsibility or fault for a situation, problem, or outcome is attributed to the current officeholder or authority in power.
- F. None of above. chosen
Provenance (4 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25e0a23c0819083abee28b2dea49c |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b77e028819087e606fc321219f7 |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25e06dd7c8190a8cbb76cee3c6e4b |
completed | Feb. 28, 2026, 3:16 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.