Triple
T29073598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dukes of Somerset |
E735873
|
entity |
| Predicate | currentFamilySeat |
P1912
|
FINISHED |
| Object | Maiden Bradley House |
—
|
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: Maiden Bradley House | Statement: [Dukes of Somerset, currentFamilySeat, Maiden Bradley House]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentFamilySeat Context triple: [Dukes of Somerset, currentFamilySeat, Maiden Bradley House]
-
A.
familySeat
chosen
Indicates the traditional principal residence or ancestral home associated with a particular family or lineage.
-
B.
hasFamilySeatNear
Indicates that an entity’s principal family residence or ancestral seat is located in the vicinity of another specified place or entity.
-
C.
familySeatFunction
Indicates that a location serves as the principal seat, residence, or base associated with a particular family or lineage.
-
D.
familySeatGiftedBy
Indicates that a family seat (such as an estate or ancestral property) was granted or given to someone by a specified donor.
-
E.
laterFamilySeat
Indicates that one entity serves as a subsequent or later seat, residence, or base for a particular family or lineage, following an earlier one.
- 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_69fd49f6dbac81909744373a357b7982 |
completed | May 8, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69fd48ed68f481908374183c66a6b055 |
completed | May 8, 2026, 2:22 a.m. |
Created at: April 28, 2026, 10:21 a.m.