Triple
T38389386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunsford parsonage |
E899666
|
entity |
| Predicate | patronOfClergyman |
P165270
|
FINISHED |
| Object | Lady Catherine de Bourgh |
—
|
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: Lady Catherine de Bourgh | Statement: [Hunsford parsonage, patronOfClergyman, Lady Catherine de Bourgh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patronOfClergyman Context triple: [Hunsford parsonage, patronOfClergyman, Lady Catherine de Bourgh]
-
A.
patron of
chosen
Indicates a supportive relationship in which one entity provides sponsorship, protection, or backing to another, often enabling its activities or development.
-
B.
clergymanTo
Indicates a relationship where one entity serves as or acts in the role of a clergyman in relation to another entity.
-
C.
religiousPatronageIn
Indicates that an entity provides religious patronage, support, or sponsorship within a specified place or region.
-
D.
memberOfClergy
Indicates that one entity serves in an official religious or clerical role within a religious organization or institution.
-
E.
hasCathedralPatron
Indicates that a person or entity serves as the patron or primary supporter of a particular cathedral.
- 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.