Triple
T5173913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swinbrook |
E116748
|
entity |
| Predicate | churchyardContains |
P48762
|
FINISHED |
| Object | graves of Mitford family members |
—
|
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: graves of Mitford family members | Statement: [Swinbrook, churchyardContains, graves of Mitford family members]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: churchyardContains Context triple: [Swinbrook, churchyardContains, graves of Mitford family members]
-
A.
hasCemetery
Indicates that one entity possesses, contains, or includes a cemetery associated with it.
-
B.
hasChurchyardUse
chosen
Indicates that a place or property is used, in whole or in part, as a churchyard or burial ground associated with a church.
-
C.
locatedInCemetery
Indicates that one entity is situated within the grounds or area of a cemetery.
-
D.
isCemeteryFor
Indicates that one entity serves as the burial ground designated for another entity, such as a community, group, or location.
-
E.
hasNearbyCemetery
Indicates that one entity is located close to, or in the immediate vicinity of, a cemetery associated with 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_69bd445ff97c81909a2615cc56235470 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd796f7c308190a721e33aabd499ac |
completed | March 20, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69bd77b529948190b86671ebe43f4734 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:45 p.m.