Triple
T2746993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château de Malmaison |
E60892
|
entity |
| Predicate | deathYearOfJoséphine |
P16526
|
FINISHED |
| Object | 1814 |
—
|
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: 1814 | Statement: [Château de Malmaison, deathYearOfJoséphine, 1814]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathYearOfJoséphine Context triple: [Château de Malmaison, deathYearOfJoséphine, 1814]
-
A.
successorAsEmpressOfTheFrench
Indicates that one person became the next Empress of the French following another person in that imperial role.
-
B.
predecessorAsEmpressOfTheFrench
Indicates that one person previously held the title Empress of the French before another person, in a direct succession.
-
C.
deathYearApproximate
Indicates that the year of an entity’s death is known only approximately rather than as an exact calendar year.
-
D.
yearOfDeath
chosen
Indicates the specific year in which an entity (typically a person or organism) died.
-
E.
notableBearerDeathYear
Indicates the year in which a notable bearer of the referenced name, title, or role died.
- 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_69ab4b79846081909096725374d65ce9 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb4ed6bc8190876c1d188b97692b |
completed | March 7, 2026, 8:01 a.m. |
| PD | Predicate disambiguation | batch_69abd829f1e88190aab1d54f87c69714 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:56 p.m.