Triple
T3896274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Self-Portrait (1654) |
E88177
|
entity |
| Predicate | positionInCreatorCareer |
P37944
|
FINISHED |
| Object | late work |
—
|
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: late work | Statement: [Self-Portrait (1654), positionInCreatorCareer, late work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInCreatorCareer Context triple: [Self-Portrait (1654), positionInCreatorCareer, late work]
-
A.
positionOnCreators
Indicates that one entity holds a specific stance, opinion, or evaluative position regarding the creators of another entity.
-
B.
refersToEraOfCareer
chosen
Indicates that one entity specifies or denotes the particular era or phase within another entity’s career.
-
C.
debutedAtPosition
Indicates the initial rank or placement an entity achieved on a specified chart, list, or ranking at the time of its first appearance.
-
D.
creatorOccupation
Indicates the professional role or job that the creator of an entity holds or held.
-
E.
partOfCareer
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
- 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_69aed9466d548190939f5217a23ed4ac |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef1abe2dc81909c18aeae9b286898 |
completed | March 9, 2026, 4:13 p.m. |
| PD | Predicate disambiguation | batch_69aee75b5b808190a348a31b1325d3d0 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:21 p.m.