Triple
T35477527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame Adelaide Bonfamille |
E1025375
|
entity |
| Predicate | languageOfOriginalSetting |
P5459
|
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: [Madame Adelaide Bonfamille, languageOfOriginalSetting, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfOriginalSetting Context triple: [Madame Adelaide Bonfamille, languageOfOriginalSetting, French]
-
A.
originalLanguageSupport
Indicates that one entity provides or maintains functionality, content, or interaction in the original language of another entity.
-
B.
languageOfOriginalDescription
Indicates that something is expressed or documented in its initial or source language version.
-
C.
originalLanguageText
Indicates that a text is expressed in its original, untranslated language.
-
D.
originalTextLanguage
chosen
Indicates the language in which a text was originally written or created before any translation or adaptation.
-
E.
originalLanguageVersionRecordedIn
Indicates that the original-language version of a work was recorded in a specified medium, format, or recording context.
- 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_69f76dfadba0819083456aadcd6864ea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a00c3362dcc819096e49b882709fddd |
completed | May 10, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_6a00c2e5cdd88190a5f2d0f6a843cd56 |
completed | May 10, 2026, 5:39 p.m. |
Created at: May 3, 2026, 4:04 p.m.