Triple
T4884502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government of Lebanon |
E109406
|
entity |
| Predicate | cabinetRequires |
P59611
|
FINISHED |
| Object | vote of confidence from Parliament |
—
|
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: vote of confidence from Parliament | Statement: [Government of Lebanon, cabinetRequires, vote of confidence from Parliament]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cabinetRequires Context triple: [Government of Lebanon, cabinetRequires, vote of confidence from Parliament]
-
A.
hasCabinet
Indicates that one entity possesses, includes, or is equipped with a cabinet associated with it.
-
B.
cabinetType
Indicates the specific kind or category of cabinet associated with an entity.
-
C.
cabinet
Indicates that one entity serves as a cabinet (a storage or enclosure unit) for another entity.
-
D.
isInCabinet
Indicates that one entity serves as a member of the governing cabinet associated with another entity (such as a government or administration).
-
E.
cabinetSeat
Indicates that an individual holds a position or seat within a governing cabinet or executive council.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6de253ac8190b1112da6953fa4f2 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6d5976a081909090c0c263f6e9b7 |
completed | March 20, 2026, 3:52 p.m. |
Created at: March 20, 2026, 1:27 p.m.