Triple
T28220922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Dr. Gachet |
E711452
|
entity |
| Predicate | creatorDeathProximity |
P28122
|
FINISHED |
| Object | painted in final months of Vincent van Gogh's life |
—
|
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: painted in final months of Vincent van Gogh's life | Statement: [Portrait of Dr. Gachet, creatorDeathProximity, painted in final months of Vincent van Gogh's life]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creatorDeathProximity Context triple: [Portrait of Dr. Gachet, creatorDeathProximity, painted in final months of Vincent van Gogh's life]
-
A.
killedNear
Indicates that one entity killed another in close spatial proximity to a specified location or reference point.
-
B.
deathApprox
chosen
Indicates that an entity’s death occurred at an approximate, rather than exact, time or date.
-
C.
deathTriggers
Indicates that the occurrence of one entity’s death causes or initiates another event, state, or process.
-
D.
deathBy
Indicates a relationship where one entity’s death is caused by another entity, event, or factor.
-
E.
deathLeadsTo
Indicates that one entity’s death causes, results in, or brings about another event, state, or condition.
- 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_69efb51dfb048190ada79b745c33b363 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: April 27, 2026, 10:46 p.m.