Triple
T236337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cross of Saint George |
E4831
|
entity |
| Predicate | visualDescription |
P5819
|
FINISHED |
| Object | red upright cross on a white field |
—
|
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: red upright cross on a white field | Statement: [Cross of Saint George, visualDescription, red upright cross on a white field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualDescription Context triple: [Cross of Saint George, visualDescription, red upright cross on a white field]
-
A.
describes
Indicates that one entity provides an explanation, representation, or account of another entity or concept.
-
B.
describedIn
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
C.
vision
Indicates that an entity perceives another entity or object visually, using sight.
-
D.
depicts
Indicates that one entity visually represents, portrays, or shows another entity.
-
E.
logoDescription
chosen
Indicates a textual description that explains the appearance, style, or content of a logo.
- 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_69a257c3d0708190b0871c4269d273e6 |
completed | Feb. 28, 2026, 2:49 a.m. |
| NER | Named-entity recognition | batch_69a25ccab7648190be6e4f5febc1e313 |
completed | Feb. 28, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69a25b5dc640819092669575731c393f |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.