Triple
T16367944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Correspondência de Fradique Mendes |
E397483
|
entity |
| Predicate | workLanguageVariant |
P123131
|
FINISHED |
| Object | European Portuguese |
—
|
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: European Portuguese | Statement: [Correspondência de Fradique Mendes, workLanguageVariant, European Portuguese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workLanguageVariant Context triple: [Correspondência de Fradique Mendes, workLanguageVariant, European Portuguese]
-
A.
languageVariant
Indicates that one language is a variant, dialect, or localized form of another language.
-
B.
officialLanguageVariant
Indicates that one language variety is an officially recognized form or version of another language within a specific jurisdiction or context.
-
C.
linguisticVariant
Indicates that one linguistic form is an alternative version or expression of another within the same or closely related language context.
-
D.
languageVariants
Indicates that one language form is a variant or alternative version of another language.
-
E.
brandLanguageVariant
Indicates that one language variant of a brand is related to or derived from another language version of the same brand.
- F. None of above. chosen
Provenance (4 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff3f0694819097faa1c1447a9e97 |
completed | April 18, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
| PDg | Predicate description generation | batch_69e24555bb6c8190977cf5c5f9149056 |
completed | April 17, 2026, 2:36 p.m. |
Created at: April 10, 2026, 5:08 a.m.