Triple
T29073592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dukes of Somerset |
E735873
|
entity |
| Predicate | seatHistoric |
P146715
|
FINISHED |
| Object | Berry Pomeroy Castle |
—
|
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: Berry Pomeroy Castle | Statement: [Dukes of Somerset, seatHistoric, Berry Pomeroy Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seatHistoric Context triple: [Dukes of Somerset, seatHistoric, Berry Pomeroy Castle]
-
A.
hasHistoricalSeat
Indicates that an entity possesses or is associated with a historically significant seat, location, or place of authority.
-
B.
familySeatHistorically
chosen
Indicates that a particular location historically served as the principal residence or ancestral seat of a specific family or lineage.
-
C.
seatSince
Indicates that an entity has held a particular seat, position, or place continuously since a specified point in time.
-
D.
seatTraditionallyAssociated
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.
-
E.
seatLocatedIn
Indicates that a seat is situated within or belongs to a specific location or area.
- 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_69f077e9b0a48190bb79548279cb7f64 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f660fc394c8190846af2f6190fcffe |
completed | May 2, 2026, 8:39 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 10:21 a.m.