Triple
T164274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ginevra de’ Benci |
E2976
|
entity |
| Predicate | reverseDepicts |
P1581
|
FINISHED |
| Object | wreath of laurel, palm, and juniper |
—
|
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: wreath of laurel, palm, and juniper | Statement: [Ginevra de’ Benci, reverseDepicts, wreath of laurel, palm, and juniper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reverseDepicts Context triple: [Ginevra de’ Benci, reverseDepicts, wreath of laurel, palm, and juniper]
-
A.
depicts
chosen
Indicates that one entity visually represents, portrays, or shows another entity.
-
B.
reverseInscription
Indicates that one entity is inscribed as the reverse or mirror image of another entity’s inscription.
-
C.
reflects
Indicates that one entity (often a surface, medium, or representation) throws back, mirrors, or otherwise shows an image, property, or state of another entity.
-
D.
describes
Indicates that one entity provides an explanation, representation, or account of another entity or concept.
-
E.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
- 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_69a2524ce1e48190ab066bf72859f474 |
completed | Feb. 28, 2026, 2:26 a.m. |
| NER | Named-entity recognition | batch_69a258827da481909b20ea5e9d21676f |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2566392208190a538ea9aa1fac53e |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:34 a.m.