Triple
T32604763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wace's Roman de Brut |
E833475
|
entity |
| Predicate | sourceLanguageOfBaseText |
P71670
|
FINISHED |
| Object | Latin |
—
|
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: Latin | Statement: [Wace's Roman de Brut, sourceLanguageOfBaseText, Latin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceLanguageOfBaseText Context triple: [Wace's Roman de Brut, sourceLanguageOfBaseText, Latin]
-
A.
originalTextLanguage
Indicates the language in which a text was originally written or created before any translation or adaptation.
-
B.
sourceLanguageMeaning
Indicates that one entity expresses the meaning or sense of another entity in a particular source language.
-
C.
indirectOriginLanguage
Indicates that something originates from a particular language, not directly but through one or more intermediate languages or sources.
-
D.
originalLanguageText
Indicates that a text is expressed in its original, untranslated language.
-
E.
languageTranslatedFrom
chosen
Indicates that a language is the source/original language from which content has been translated into another language.
- 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_69f3492ab63c8190aec24d5003b47c29 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: May 1, 2026, 1:05 a.m.