Triple
T18336225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eugen Sandow |
E439275
|
entity |
| Predicate | modeledPhysiqueOn |
P94907
|
FINISHED |
| Object | classical Greek sculpture |
—
|
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: classical Greek sculpture | Statement: [Eugen Sandow, modeledPhysiqueOn, classical Greek sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modeledPhysiqueOn Context triple: [Eugen Sandow, modeledPhysiqueOn, classical Greek sculpture]
-
A.
modeledBy
Indicates that one entity serves as a model or representation of another, typically capturing its structure, behavior, or properties.
-
B.
modeledWith
Indicates that something is represented, simulated, or described using a particular model, method, or modeling technique.
-
C.
residesOverBodyType
Indicates that one entity is positioned or located above another entity that is characterized by a specific body type.
-
D.
bodyDesigner
Indicates that one entity is responsible for designing, shaping, or creating the physical form or structure of another entity.
-
E.
impactOnBodyIdeal
chosen
Indicates the effect that something has on shaping, reinforcing, or altering perceptions of the ideal body.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecd759481909703ed2d0d68199f |
completed | April 19, 2026, 5:20 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.