Triple
T18078831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Somerset |
E432629
|
entity |
| Predicate | seatTraditionally |
P16984
|
FINISHED |
| Object | Somerset and surrounding counties |
—
|
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: Somerset and surrounding counties | Statement: [Duke of Somerset, seatTraditionally, Somerset and surrounding counties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seatTraditionally Context triple: [Duke of Somerset, seatTraditionally, Somerset and surrounding counties]
-
A.
seatTraditionallyAssociated
chosen
Indicates that one entity is a seat or position that is customarily or historically linked with another entity, such as a role, office, or title.
-
B.
seatOn
Indicates that one entity is positioned or placed on a seat or seating surface associated with another entity.
-
C.
seatForm
Indicates that one entity serves as the physical seating structure or configuration associated with another entity.
-
D.
seatIs
Indicates that one entity functions as the seat or seating position of another entity.
-
E.
seatCategory
Indicates the classification or type of a seat (e.g., by comfort level, price tier, or section) assigned to an 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4d9f6a85481909894c39c8be98d5d |
completed | April 19, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69e3f90c652481908133a73106d78919 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:27 a.m.