Triple
T17783245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shavasana I |
E443949
|
entity |
| Predicate | usesVisualLanguage |
P82532
|
FINISHED |
| Object | surreal imagery |
—
|
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: surreal imagery | Statement: [Shavasana I, usesVisualLanguage, surreal imagery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesVisualLanguage Context triple: [Shavasana I, usesVisualLanguage, surreal imagery]
-
A.
languageModality
Indicates the mode or form in which a language is expressed or perceived (e.g., spoken, signed, written, or tactile).
-
B.
hasLanguageDepiction
Indicates that one entity is depicted, represented, or expressed using the language or linguistic form of another entity.
-
C.
visuallyDefines
Indicates that one entity establishes or clarifies the appearance, form, or visual characteristics of another entity.
-
D.
usesLanguageFor
Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
-
E.
visualMetaphor
chosen
Indicates a relationship where one entity conceptually represents or explains another through a visual analogy or symbolic imagery.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e487234fc08190b590f20caa431463 |
completed | April 19, 2026, 7:41 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:12 a.m.