Triple
T28304845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louise de Kérouaille, Duchess of Portsmouth |
E713810
|
entity |
| Predicate | createdDuchessOfPortsmouthInYear |
P190482
|
FINISHED |
| Object | 1673 |
—
|
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: 1673 | Statement: [Louise de Kérouaille, Duchess of Portsmouth, createdDuchessOfPortsmouthInYear, 1673]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdDuchessOfPortsmouthInYear Context triple: [Louise de Kérouaille, Duchess of Portsmouth, createdDuchessOfPortsmouthInYear, 1673]
-
A.
createdDuchessOfPortsmouthBy
Indicates that an authority or agent established or conferred the title of Duchess of Portsmouth upon a specific person.
-
B.
createdDuchess
Indicates that an entity brought a duchess into existence, typically by giving birth to or otherwise originating her.
-
C.
dateBecamePrincessRoyal
Indicates the specific date on which an individual assumed the title or status of Princess Royal.
-
D.
yearDeclaredPatroness
Indicates the specific year in which an entity was formally declared as a patroness of someone or something.
-
E.
createdDukeOfRichmondDate
Indicates the date on which the title of Duke of Richmond was created or conferred.
- F. None of above. chosen
Provenance (4 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcc7779d248190afdb348a95375443 |
completed | May 7, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
| PDg | Predicate description generation | batch_69fcc73264e08190b0b5917f32226fae |
completed | May 7, 2026, 5:09 p.m. |
Created at: April 27, 2026, 11:37 p.m.