Triple
T1386972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senate of France |
E29867
|
entity |
| Predicate | renewalFraction |
P5690
|
FINISHED |
| Object | half of the seats every 3 years |
—
|
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: half of the seats every 3 years | Statement: [Senate of France, renewalFraction, half of the seats every 3 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: renewalFraction Context triple: [Senate of France, renewalFraction, half of the seats every 3 years]
-
A.
renewalPattern
chosen
Indicates the recurring schedule or frequency with which something is renewed or repeated over time.
-
B.
renewalTerm
Indicates the length or conditions of time for which an agreement, contract, or subscription is extended beyond its initial term.
-
C.
renewalDate
Indicates the date on which an existing agreement, subscription, or arrangement is scheduled to be renewed or extended.
-
D.
isRenewable
Indicates that a resource or energy source can be naturally replenished or regenerated within a human-relevant timescale.
-
E.
reappointmentPolicy
Indicates the rules or conditions governing whether and how an individual can be reappointed to a position or role.
- 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_69a498dc92f8819094a1108f8ac90f43 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c33b6e108190b6b2bca4ddd97b6c |
completed | March 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69a4beffcf808190ab4cd0271257ce63 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.