Triple
T22789862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canadian Census of Population |
E564079
|
entity |
| Predicate | longFormName |
P1116
|
FINISHED |
| Object | Census of Population long-form |
—
|
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: Census of Population long-form | Statement: [Canadian Census of Population, longFormName, Census of Population long-form]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: longFormName Context triple: [Canadian Census of Population, longFormName, Census of Population long-form]
-
A.
longNameInEnglish
Indicates that an entity’s full or extended name is given in the English language.
-
B.
longTitle
chosen
Indicates that an entity has an extended or full-length title associated with it.
-
C.
officialName
Indicates the formally recognized name assigned to an entity by an authoritative body or source.
-
D.
firstOfficialName
Indicates the original or primary official name formally assigned to an entity before any subsequent name changes or alternatives.
-
E.
fullName
Indicates that an entity has a complete personal name, typically combining given name(s) and family name into a single string.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c3488708190812f7d2edac92184 |
completed | April 29, 2026, 3:34 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:29 p.m.