Triple
T4884510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government of Lebanon |
E109406
|
entity |
| Predicate | primeMinistershipReservedFor |
P59613
|
FINISHED |
| Object | Sunni Muslim |
—
|
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: Sunni Muslim | Statement: [Government of Lebanon, primeMinistershipReservedFor, Sunni Muslim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primeMinistershipReservedFor Context triple: [Government of Lebanon, primeMinistershipReservedFor, Sunni Muslim]
-
A.
primeMinisterSelectionPower
Indicates the authority or role an entity has in choosing, appointing, or influencing the selection of a prime minister.
-
B.
primeMinisterAtEnactment
Indicates that the referenced person was serving as prime minister at the time a particular law, act, or measure was enacted.
-
C.
primeMinisterFrom
Indicates that a person serves or has served as the prime minister of a specified country, region, or political entity.
-
D.
primeMinisterOf
Indicates that a person holds the office of prime minister as the head of government of a specified country or political entity.
-
E.
primeMinisterAtStart
Indicates that the subject was serving as prime minister at the beginning of a specified period or event.
- 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.