Triple
T30131174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berkshire Record Office |
E765849
|
entity |
| Predicate | documentTypeHeld |
P13313
|
FINISHED |
| Object | parish registers |
—
|
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: parish registers | Statement: [Berkshire Record Office, documentTypeHeld, parish registers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentTypeHeld Context triple: [Berkshire Record Office, documentTypeHeld, parish registers]
-
A.
documentTypeUsed
Indicates that a particular type or category of document is employed or applied in a given context or activity.
-
B.
documentTypeIncluded
chosen
Indicates that a particular document type is contained within, or is part of, a specified set or collection of document types.
-
C.
holdsDocumentsFrom
Indicates that an entity possesses or retains documents that originate from or are issued by another specified entity.
-
D.
documentationType
Indicates the specific category or kind of documentation associated with or required for an entity or process.
-
E.
documentTypeProduced
Indicates that one entity produces, generates, or creates a document of a specified type.
- 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_69f22477d1a081908df2b7e6ed16859d |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6abaa1f648190b77073771df3bf3b |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 29, 2026, 7:15 p.m.