Triple
T24085483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johanna van Gogh-Bonger |
E596630
|
entity |
| Predicate | editedCorrespondenceOf |
P139756
|
FINISHED |
| Object | Vincent van Gogh |
—
|
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: Vincent van Gogh | Statement: [Johanna van Gogh-Bonger, editedCorrespondenceOf, Vincent van Gogh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editedCorrespondenceOf Context triple: [Johanna van Gogh-Bonger, editedCorrespondenceOf, Vincent van Gogh]
-
A.
editedTo
Indicates that one entity has been modified, revised, or altered in order to become the other entity.
-
B.
correspondedWith
Indicates that two entities engaged in mutual communication, typically by exchanging messages or letters over a period of time.
-
C.
editedIn
Indicates that an entity was modified, revised, or otherwise altered within a particular context, tool, environment, or time frame.
-
D.
relatedCorrespondence
chosen
Indicates that there exists a piece of correspondence (such as a letter, email, or message) that is associated with or pertains to the related entity.
-
E.
includesCorrectionsFor
Indicates that one item contains modifications, fixes, or amendments that address errors or issues present in another item.
- 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_69e288c4638c81909bacc28a1e3d436b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dc28a7cc81909c76d9d992ac21dc |
completed | April 29, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 10:44 p.m.