Triple
T34297392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alfred Wallis |
E880068
|
entity |
| Predicate | startedPaintingAfter |
P69015
|
FINISHED |
| Object | death of his wife |
—
|
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: death of his wife | Statement: [Alfred Wallis, startedPaintingAfter, death of his wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startedPaintingAfter Context triple: [Alfred Wallis, startedPaintingAfter, death of his wife]
-
A.
startedPainting
chosen
Indicates that an entity began the activity or process of painting, marking the initiation of that action.
-
B.
paintedOn
Indicates that one entity has been applied as paint onto the surface of another entity.
-
C.
paintingPractice
Indicates engaging in the activity of practicing or improving skills in painting.
-
D.
paintedEvery
Indicates that an entity applied paint to each and every relevant item in a specified set or domain.
-
E.
paintedIn
Indicates that an artwork or object was created or executed using paint within a specific time period or at a particular location.
- 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_69f349b79f6c81909cb468c92c39c74d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a001540d4f881908a4688881875e774 |
completed | May 10, 2026, 5:18 a.m. |
| PD | Predicate disambiguation | batch_6a0014a8cdd88190a67a90a2df2c5e18 |
completed | May 10, 2026, 5:16 a.m. |
Created at: May 1, 2026, 1:57 a.m.