Triple
T9631334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quebec general election |
E232809
|
entity |
| Predicate | heldAtLeastEvery |
P7174
|
FINISHED |
| Object | 5 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: 5 years | Statement: [Quebec general election, heldAtLeastEvery, 5 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldAtLeastEvery Context triple: [Quebec general election, heldAtLeastEvery, 5 years]
-
A.
heldEvery
Indicates that an entity consistently possessed or maintained control of another entity throughout every instance or period within a specified range.
-
B.
meetsEvery
Indicates that one entity encounters or comes into contact with every member of a specified set of entities.
-
C.
occursEvery
chosen
Indicates that an event or action happens repeatedly at regular, specified intervals.
-
D.
laterFrequency
Indicates that one event, state, or action occurs with a lower frequency than another in a temporal sequence.
-
E.
holdsApproximatelyFor
Indicates that a condition, relation, or value is valid only to an approximate degree or within a tolerance, rather than holding exactly.
- 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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b2621408190bfe2ea5a05359ee0 |
completed | April 1, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.