Triple
T11117646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eve (Rodin sculpture) |
E262928
|
entity |
| Predicate | has version |
P30547
|
FINISHED |
| Object | plaster cast |
—
|
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: plaster cast | Statement: [Eve (Rodin sculpture), has version, plaster cast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: has version Context triple: [Eve (Rodin sculpture), has version, plaster cast]
-
A.
hasVersionIn
Indicates that one entity exists as a specific version or variant within the context, format, or system represented by another entity.
-
B.
hasVersionNumber
Indicates that an entity is associated with a specific version identifier or number.
-
C.
has edition or version
chosen
Indicates that one entity exists as a particular edition or version of another entity.
-
D.
hasVersionStatus
Indicates that an entity is associated with a particular version state or status within its lifecycle or revision history.
-
E.
hasVersionType
Indicates that one entity is associated with a specific kind or category of version of 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79af638b08190b7ade5eb0cab6b75 |
completed | April 9, 2026, 12:26 p.m. |
| PD | Predicate disambiguation | batch_69d7441cf8188190b8095f622c923156 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.