Triple
T29418094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matteo Salvini |
E746079
|
entity |
| Predicate | officeForEndTime |
P123562
|
FINISHED |
| Object | Deputy Prime Minister of Italy |
—
|
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: Deputy Prime Minister of Italy | Statement: [Matteo Salvini, officeForEndTime, Deputy Prime Minister of Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeForEndTime Context triple: [Matteo Salvini, officeForEndTime, Deputy Prime Minister of Italy]
-
A.
officeEndTimeFor
Indicates the time at which an entity’s office hours or work period end for another specified entity.
-
B.
officeEndApproximate
Indicates that an office or term ended around an approximate date rather than on a precisely known day.
-
C.
officeForStartEndTime
Indicates that an office is assigned or valid for a specific time interval defined by a start time and an end time.
-
D.
previousOfficeEndTime
Indicates the time at which an entity’s immediately preceding office or position ended.
-
E.
officeEndTimeForPosition
chosen
Indicates the time at which a given position or role’s term of office ends.
- 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_69f0a79f6d5c8190a350baed0157e06f |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fde9fc184c8190bebef35df0e76076 |
completed | May 8, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69fde6e5beb4819094945a695e961d88 |
completed | May 8, 2026, 1:36 p.m. |
Created at: April 28, 2026, 3:02 p.m.