Triple
T7335084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George FitzRoy, 1st Duke of Northumberland |
E169105
|
entity |
| Predicate | createdDuke |
P65688
|
FINISHED |
| Object | 1683 |
—
|
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: 1683 | Statement: [George FitzRoy, 1st Duke of Northumberland, createdDuke, 1683]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdDuke Context triple: [George FitzRoy, 1st Duke of Northumberland, createdDuke, 1683]
-
A.
createdDukeOn
Indicates that an entity established or founded the title or position of Duke on a specific date or occasion.
-
B.
createdDukeBy
chosen
Indicates that an entity was made a duke (granted the ducal title or rank) by another specific entity.
-
C.
createdDukeOfElchingen
Indicates the act of conferring the noble title "Duke of Elchingen" upon a person, thereby creating or establishing that dukedom for them.
-
D.
createdDukeOfExeter
Indicates that one entity granted or established the noble title "Duke of Exeter" for another entity.
-
E.
createdDukeOfFifeBy
Indicates that one entity conferred or established the title "Duke of Fife" upon another entity.
- 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_69c68a568a6481908f11e20db7bc8446 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f347f25081908e6086d4073295f5 |
completed | March 27, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69c6f028fd748190b2ea5c3081958a42 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:04 p.m.