Triple
T22072958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palazzo Spada courtyard |
E545454
|
entity |
| Predicate | illusionType |
P101847
|
FINISHED |
| Object | forced perspective |
—
|
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: forced perspective | Statement: [Palazzo Spada courtyard, illusionType, forced perspective]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: illusionType Context triple: [Palazzo Spada courtyard, illusionType, forced perspective]
-
A.
illusionCategory
Indicates the type or class of illusion to which an illusion-related entity or phenomenon belongs.
-
B.
typeOfDeception
Indicates the specific kind or category of deceptive act that one entity employs toward another or in a given context.
-
C.
hasOpticalIllusionType
chosen
Indicates that an entity exhibits or is associated with a specific type or category of optical illusion.
-
D.
gimmick
Indicates that an entity uses or features a novel, attention-grabbing trick or device primarily intended to attract interest rather than provide substantive value.
-
E.
deceptionMotif
Indicates a relationship where one entity employs or embodies a theme of deceit, trickery, or misleading appearance in relation to another entity or situation.
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12889f504819089830202e64d97b0 |
completed | April 28, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69e6f64a6a70819089d1a6c3a2384861 |
completed | April 21, 2026, 4 a.m. |
Created at: April 16, 2026, 8:28 p.m.