Triple
T24328195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heaven and Hell |
E613159
|
entity |
| Predicate | panelArrangement |
P46737
|
FINISHED |
| Object | triptych |
—
|
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: triptych | Statement: [Heaven and Hell, panelArrangement, triptych]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: panelArrangement Context triple: [Heaven and Hell, panelArrangement, triptych]
-
A.
arrangement
Indicates a relationship where entities are organized, ordered, or positioned in a particular configuration or sequence relative to one another.
-
B.
arranges
Indicates that one entity organizes, coordinates, or puts in order some event, objects, or circumstances involving another entity.
-
C.
arrangementType
chosen
Indicates the specific kind or category of arrangement that characterizes how the related entities are organized or structured in relation to each other.
-
D.
featuresArrangementBy
Indicates that one entity determines or specifies the spatial or structural arrangement of features in another entity.
-
E.
typicalWindowArrangement
Indicates the usual or standard spatial configuration in which windows are arranged relative to each other in a given context.
- 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_69e2d7db6d5c819091194918157a7c1f |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292eebf7081908ef50ef331ff88aa |
completed | April 29, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:54 a.m.