Triple
T8489035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Invisible Connections |
E200909
|
entity |
| Predicate | hasArtworkFeature |
P68894
|
FINISHED |
| Object | abstract geometric 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: abstract geometric imagery | Statement: [Invisible Connections, hasArtworkFeature, abstract geometric imagery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArtworkFeature Context triple: [Invisible Connections, hasArtworkFeature, abstract geometric imagery]
-
A.
hasArtFeature
chosen
Indicates that an entity possesses or is characterized by a particular artistic attribute, element, or stylistic feature.
-
B.
hasOfficialArtwork
Indicates that an entity is associated with an officially sanctioned piece of artwork representing it.
-
C.
hasPublicArtwork
Indicates that a location or entity possesses or features artwork that is accessible to the general public.
-
D.
hasCoverArtFeaturing
Indicates that one entity’s cover art visually features or depicts another entity.
-
E.
hasArtCollection
Indicates that an entity possesses, maintains, or is associated with a collection of artworks.
- 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_69ca831d7b148190a6e32c1de43ab13b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5581d308190b47d76dd49a36529 |
completed | March 31, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69cbd107633c8190a36ba50e07876918 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:13 p.m.