Triple
T5243663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Beaufort, Duke of Exeter |
E118405
|
entity |
| Predicate | createdEarlOfDorset |
P37514
|
FINISHED |
| Object | 5 July 1411 |
—
|
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: 5 July 1411 | Statement: [Thomas Beaufort, Duke of Exeter, createdEarlOfDorset, 5 July 1411]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdEarlOfDorset Context triple: [Thomas Beaufort, Duke of Exeter, createdEarlOfDorset, 5 July 1411]
-
A.
createdDukeOfYorkBy
Indicates the action by which an authority or agent formally conferred or established the title of Duke of York upon a person.
-
B.
createdDukeOfClarence
Indicates the relationship in which one entity formally granted or established the noble title "Duke of Clarence" for another entity.
-
C.
createdEarlBy
chosen
Indicates that an entity was granted or established as an earl by a specific creator or authority.
-
D.
createdDukeOfFifeBy
Indicates that one entity conferred or established the title "Duke of Fife" upon another entity.
-
E.
createdViscountIn
Indicates that an entity conferred or established the noble title of viscount in a particular place, context, or jurisdiction.
- 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b4da7308190856cdcee9cca41eb |
completed | March 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69bd77c1397c8190a7fd844d7a396e54 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:49 p.m.