Triple
T31539355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John, Duke of Rothes |
E804700
|
entity |
| Predicate | successorAsDukeOfRothes |
P198788
|
FINISHED |
| Object | Margaret Leslie, 8th Countess of Rothes |
—
|
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: Margaret Leslie, 8th Countess of Rothes | Statement: [John, Duke of Rothes, successorAsDukeOfRothes, Margaret Leslie, 8th Countess of Rothes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorAsDukeOfRothes Context triple: [John, Duke of Rothes, successorAsDukeOfRothes, Margaret Leslie, 8th Countess of Rothes]
-
A.
successorAsDuke
Indicates that one person directly follows another in holding the title and position of duke.
-
B.
successorAsDukeOfYork
Indicates that one person became the next holder of the title Duke of York after another person.
-
C.
successorAsDukeOfKentAndStrathearn
Indicates that one entity became the next holder of the title "Duke of Kent and Strathearn" after another entity.
-
D.
successorAsDukeOfNorfolk
Indicates that one entity became the next holder of the title Duke of Norfolk after another entity.
-
E.
successorAsDukeOfOrléans
Indicates that one entity became the next holder of the title Duke of Orléans after another entity.
- 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_69f348d03ef88190a2b73d7b94b9e02d |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff069ec1348190815375c5c9e38404 |
completed | May 9, 2026, 10:04 a.m. |
| PD | Predicate disambiguation | batch_69ff05ba57f88190a45d20f18044e0fb |
completed | May 9, 2026, 10 a.m. |
| PDg | Predicate description generation | batch_69ff069ddf948190bdfe438953249dd0 |
completed | May 9, 2026, 10:04 a.m. |
Created at: April 30, 2026, 10:05 p.m.