Triple
T33495607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bona |
E857854
|
entity |
| Predicate | numberInLatinMorphology |
P204098
|
FINISHED |
| Object | plural of bonum in some constructions |
—
|
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: plural of bonum in some constructions | Statement: [Bona, numberInLatinMorphology, plural of bonum in some constructions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberInLatinMorphology Context triple: [Bona, numberInLatinMorphology, plural of bonum in some constructions]
-
A.
numberOfGrammaticalCases
Indicates the relationship that specifies how many distinct grammatical cases a language or linguistic system possesses.
-
B.
latinGenitive
Indicates that one entity is in the Latin genitive case in relation to another, typically expressing possession, origin, or association.
-
C.
hasLatinAdjectiveForm
Indicates that an entity has a corresponding adjectival form in Latin derived from its name or designation.
-
D.
openingWordsLatin
Indicates that the opening words of a text, work, or document are expressed in Latin.
-
E.
hasGrammaticalGenderInLatin
Indicates that an entity possesses a specific grammatical gender (masculine, feminine, or neuter) in the Latin language.
- 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_69f3497660508190a541826a81f7e9ab |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a03232efd8481908ee25447a29ee20b |
completed | May 12, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_6a032269dcb08190907c965c28145b77 |
completed | May 12, 2026, 12:51 p.m. |
| PDg | Predicate description generation | batch_6a03232e53788190abf17396e8d02dbf |
completed | May 12, 2026, 12:55 p.m. |
Created at: May 1, 2026, 1:38 a.m.