Triple
T15307545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Trench |
E365941
|
entity |
| Predicate | positionInCreatorWork |
P19302
|
FINISHED |
| Object | major work of Otto Dix |
—
|
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: major work of Otto Dix | Statement: [The Trench, positionInCreatorWork, major work of Otto Dix]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInCreatorWork Context triple: [The Trench, positionInCreatorWork, major work of Otto Dix]
-
A.
positionOnCreators
Indicates that one entity holds a specific stance, opinion, or evaluative position regarding the creators of another entity.
-
B.
positionInAuthorOeuvre
chosen
Indicates the relative placement or order of a work within an author's overall body of work.
-
C.
positionInWork
Indicates the specific role, rank, or placement an entity holds within a larger work or structured composition.
-
D.
relatedWorkCreator
Indicates that the creator of one work is related (e.g., by authorship, contribution, or collaboration) to the creation of another work.
-
E.
positionOfAuthor
Indicates the spatial or organizational location associated with an author in relation to some reference context.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd001b48190bbdd69337efdb907 |
completed | April 16, 2026, 1:35 a.m. |
| PD | Predicate disambiguation | batch_69deca935e2c8190b640987ddfc542b9 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:16 a.m.