Triple
T31329024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General council of France |
E798973
|
entity |
| Predicate | couldLevy |
P41654
|
FINISHED |
| Object | local taxes |
—
|
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: local taxes | Statement: [General council of France, couldLevy, local taxes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couldLevy Context triple: [General council of France, couldLevy, local taxes]
-
A.
canLevy
chosen
Indicates that an entity has the authority or power to impose and collect a charge, tax, or fine on another entity or resource.
-
B.
canElect
Indicates that one entity has the authority or ability to choose another entity for a position, role, or office through an election process.
-
C.
couldPass
Indicates that one entity had the ability or potential to move through, overcome, or be accepted by another entity or barrier.
-
D.
canRaise
Indicates that one entity has the ability or authority to increase, elevate, or lift another entity (such as a value, object, or status).
-
E.
canLeadTo
Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
- 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_69f224e3238c8190b2291f50ea4962cd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69ede2ea48190999b3d041f7bf55e |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1d25e88190a7f57d323574da90 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:16 p.m.