Triple
T22352424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catherine Blake |
E552565
|
entity |
| Predicate | roleInWilliamBlakesWork |
P15464
|
FINISHED |
| Object | close collaborator |
—
|
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: close collaborator | Statement: [Catherine Blake, roleInWilliamBlakesWork, close collaborator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInWilliamBlakesWork Context triple: [Catherine Blake, roleInWilliamBlakesWork, close collaborator]
-
A.
roleInArt
Indicates the specific function, position, or contribution an entity has within a particular artwork or artistic production.
-
B.
roleInParadiseLost
Indicates the specific narrative or functional role an entity plays within the work *Paradise Lost*.
-
C.
roleInKeatsLife
Indicates the specific role or relationship an entity had in the life of Keats.
-
D.
roleInRhyme
Indicates the specific function or part an entity plays within a rhyme, such as a character, object, or structural element of the rhyming text.
-
E.
notableWorkRole
chosen
Indicates that a person’s role or position is specifically associated with the creation, performance, or contribution to a notable work.
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1579cbbe88190bf2f27d34fc8f30e |
completed | April 29, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69e7300c20088190a59e5bf9e70384f3 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:44 p.m.