Triple
T1874399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Noyon, Picardy, Kingdom of France |
E39107
|
entity |
| Predicate | languageUsedHistorically |
P1434
|
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: [Noyon, Picardy, Kingdom of France, languageUsedHistorically, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageUsedHistorically Context triple: [Noyon, Picardy, Kingdom of France, languageUsedHistorically, French]
-
A.
historicallySpokenIn
chosen
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
B.
historicalLanguage
Indicates that one language is a historical or earlier form/ancestor of another language.
-
C.
languageOfHistoricalRecord
Indicates the language in which a given historical record is written or recorded.
-
D.
historicalLanguageOfEnvironment
Indicates that a language was historically used or prevalent in a given environment or setting, even if it is not the current primary language there.
-
E.
historicalLanguageGroup
Indicates that two or more entities belong to the same historically defined language group or family, based on shared linguistic ancestry or development.
- 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_69a8862f7074819096afe7fe65e179e9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0f79fbc819085c54f3189a552d9 |
completed | March 7, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69abafe2b56c81909e13d543982e6e13 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.