Triple
T38162111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McGill Law Journal |
E953044
|
entity |
| Predicate | operatingLanguagePolicy |
P73903
|
FINISHED |
| Object | bilingual |
—
|
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: bilingual | Statement: [McGill Law Journal, operatingLanguagePolicy, bilingual]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatingLanguagePolicy Context triple: [McGill Law Journal, operatingLanguagePolicy, bilingual]
-
A.
languagePolicyType
chosen
Indicates the specific category or type of language policy that governs how languages are used, managed, or regulated in a given context.
-
B.
supportsPolicyLanguage
Indicates that one entity provides compatibility with, or the ability to interpret and use, a specified policy language defined by another entity.
-
C.
languageOfRegistrationPolicies
Indicates the language in which the registration policies are written or officially specified.
-
D.
shareLanguagePolicyCooperation
Indicates that two or more entities cooperate or coordinate with each other specifically on matters related to language policy.
-
E.
mayUseLanguagesOf
Indicates that an entity is permitted to use the languages associated with another entity.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0353887e848190ad98ecbbe7bbc061 |
completed | May 12, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_6a0352dfb5648190b9f8c9b7c388d2a1 |
completed | May 12, 2026, 4:18 p.m. |
Created at: May 3, 2026, 4:21 p.m.