Triple
T27013793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicolas Oudinot |
E680468
|
entity |
| Predicate | elevationToMarshalOfFrance |
P62781
|
FINISHED |
| Object | 1809 |
—
|
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: 1809 | Statement: [Nicolas Oudinot, elevationToMarshalOfFrance, 1809]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevationToMarshalOfFrance Context triple: [Nicolas Oudinot, elevationToMarshalOfFrance, 1809]
-
A.
promotedToMarshalOfFrance
chosen
Indicates that a person has been elevated or appointed to the rank or office of Marshal of France.
-
B.
elevationRelativeToParis
Indicates the relative elevation difference between a given location and Paris, specifying how much higher or lower it is in altitude.
-
C.
elevationOfSavoyToDuchyBy
Indicates the agent or authority responsible for elevating Savoy to the status of a duchy.
-
D.
elevationToEmperorBy
Indicates the action or event in which one entity raises or appoints another entity to the rank or title of emperor.
-
E.
rankInLegionOfHonour
Indicates the specific level or grade a person holds within the hierarchy of the Legion of Honour distinction.
- 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_69eeeb53939c8190bd431f32b060f01f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 7:05 a.m.