Triple
T34948220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Work |
E1007911
|
entity |
| Predicate | isAbstractLevelOf |
P19458
|
FINISHED |
| Object | Creative expression |
—
|
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: Creative expression | Statement: [Work, isAbstractLevelOf, Creative expression]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAbstractLevelOf Context triple: [Work, isAbstractLevelOf, Creative expression]
-
A.
isAbstractClass
Indicates that a class is defined as abstract, meaning it cannot be instantiated directly and is intended to be subclassed.
-
B.
hasAbstractType
Indicates that an entity is associated with or classified under a more general, conceptual type rather than a concrete or specific instance.
-
C.
isAbstractDesignation
Indicates that one entity serves as a non-physical, conceptual, or symbolic label or designation for another entity.
-
D.
isAbstractVersionOf
chosen
Indicates that one entity represents a conceptual, generalized, or non-concrete version of another, more specific or concrete entity.
-
E.
hasStructureLevel
Indicates a relationship where one entity possesses, is assigned, or is characterized by a particular structural level within a hierarchy or layered organization.
- 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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782cb65a081909711080d90d59017 |
completed | May 3, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f781020cc4819088c40cb8589504e4 |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.