Triple
T29347815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Green Box |
E744217
|
entity |
| Predicate | isFacsimileOf |
P155065
|
FINISHED |
| Object | Marcel Duchamp's original working notes |
—
|
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: Marcel Duchamp's original working notes | Statement: [The Green Box, isFacsimileOf, Marcel Duchamp's original working notes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFacsimileOf Context triple: [The Green Box, isFacsimileOf, Marcel Duchamp's original working notes]
-
A.
includesFacsimilesOf
chosen
Indicates that an entity contains or provides reproductions or exact copies (facsimiles) of another entity or its content.
-
B.
isImprintOf
Indicates that one entity is a specific edition, printing, or imprint derived from another bibliographic entity.
-
C.
isImageOf
Indicates that one entity is a visual depiction or representation of another entity.
-
D.
isDoubleCoverOf
Indicates that one object serves as a two-to-one covering of another, such that each point or element of the second is covered by exactly two corresponding points or elements of the first.
-
E.
isCoverOf
Indicates that one entity functions as a protective or enclosing layer placed over another entity.
- 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_69f0a79a2d748190bc30abd469298b37 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f669595a0881908ea97caf704fefb3 |
completed | May 2, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69f660f4f7a88190b93c60d76b86c912 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 2:03 p.m.