Triple
T32393409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Normandin |
E827737
|
entity |
| Predicate | inProvinceWithOfficialLanguage |
P96074
|
FINISHED |
| Object | French |
—
|
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: French | Statement: [Normandin, inProvinceWithOfficialLanguage, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inProvinceWithOfficialLanguage Context triple: [Normandin, inProvinceWithOfficialLanguage, French]
-
A.
hasOfficialLanguageOfLocation
chosen
Indicates that a location has a specified language recognized as its official language.
-
B.
usesOfficialLanguageOf
Indicates that one entity adopts and employs the official language of another entity for communication or formal purposes.
-
C.
declaresOfficialLanguageOf
Indicates that an authority formally designates a particular language as the official language of a specified entity or jurisdiction.
-
D.
hasNotableLanguageWithOfficialStatusIn
Indicates that a language holds an officially recognized and notable status within a specified jurisdiction or region.
-
E.
previousOfficialLanguage
Indicates that one language formerly held official status in a country, region, or organization before being replaced or losing that status.
- 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_69f349184e7481909c6c54428cb9cf12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c2110790819083172d8a7bc831ce |
completed | May 3, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:52 a.m.