Triple
T24135373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catherine Hoskins |
E598068
|
entity |
| Predicate | nobleTitleHeldBySpouse |
P17687
|
FINISHED |
| Object | Duke of Devonshire |
—
|
NE NERFINISHED |
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: Duke of Devonshire | Statement: [Catherine Hoskins, nobleTitleHeldBySpouse, Duke of Devonshire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nobleTitleHeldBySpouse Context triple: [Catherine Hoskins, nobleTitleHeldBySpouse, Duke of Devonshire]
-
A.
hasSpouseTitle
chosen
Indicates that a person’s spouse holds a particular title or honorific designation.
-
B.
isSpouseOfTitle
Indicates that one entity holds a spousal relationship specifically associated with a titled or honorific status of another entity.
-
C.
spouseNameAfterEnnoblement
Indicates that the predicate specifies the spouse’s name as it is used after the spouse has been ennobled or granted a noble title.
-
D.
spouseNobilityStatus
Indicates that the predicate specifies the nobility rank or noble status held by a person’s spouse.
-
E.
currentTitleHolderSpouseOf
Indicates that one entity is the current spouse of the individual who presently holds a specified title.
- 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_69e288c92e448190ac57034fa0c863ce |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1df7c3ce08190bcbd9056a6630c2f |
completed | April 29, 2026, 10:37 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:26 p.m.