Triple
T32319831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue triptych |
E825743
|
entity |
| Predicate | hasPanelRelation |
P33476
|
FINISHED |
| Object | narrative or conceptual sequence |
—
|
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: narrative or conceptual sequence | Statement: [Blue triptych, hasPanelRelation, narrative or conceptual sequence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPanelRelation Context triple: [Blue triptych, hasPanelRelation, narrative or conceptual sequence]
-
A.
hasPanel
Indicates that one entity includes, is equipped with, or is associated with a panel as a component or feature.
-
B.
hasPanelType
Indicates that an entity is associated with or characterized by a specific type or category of panel.
-
C.
hasPanelComposition
Indicates that something is composed of or structured into multiple panels or panel-like sections.
-
D.
hasRelation
chosen
Indicates that there exists some specified relationship or association between two entities.
-
E.
hasPanelFormat
Indicates that something is associated with a particular panel layout or format used for its presentation or display.
- 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_69f34912d0c48190bba75770660320e9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fefa064ab48190925759950d0d94d9 |
completed | May 9, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69fef96ae5d08190b027435753c44821 |
completed | May 9, 2026, 9:07 a.m. |
Created at: May 1, 2026, 12:46 a.m.