Triple
T319946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winchester College |
E7791
|
entity |
| Predicate | founderOccupation |
P7991
|
FINISHED |
| Object | Bishop of Winchester |
—
|
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: Bishop of Winchester | Statement: [Winchester College, founderOccupation, Bishop of Winchester]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: founderOccupation Context triple: [Winchester College, founderOccupation, Bishop of Winchester]
-
A.
foundedByOccupation
chosen
Indicates that an entity (such as an organization or institution) was founded by a person or group characterized by a specific occupation or professional role.
-
B.
founder
Indicates that an entity established, created, or started another entity such as an organization, institution, or company.
-
C.
founderRole
Indicates that an entity serves as a founder in relation to another entity, specifying the role or capacity in which they established it.
-
D.
cofounderOf
Indicates that a person jointly established or created an organization, company, or project with one or more other founders.
-
E.
founderWrote
Indicates that an entity who is a founder of something is also the author or writer of a specified work or text.
- 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ea7edbc48190b9031bd1af48f72a |
completed | Feb. 28, 2026, 1:15 p.m. |
| PD | Predicate disambiguation | batch_69a2e946607081909c8b97473aaf8d1b |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.