Triple
T38377863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дворцовый мост |
E893673
|
entity |
| Predicate | частоИзображаетсяНа |
P34220
|
FINISHED |
| Object | открытки Санкт-Петербурга |
—
|
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: открытки Санкт-Петербурга | Statement: [Дворцовый мост, частоИзображаетсяНа, открытки Санкт-Петербурга]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: частоИзображаетсяНа Context triple: [Дворцовый мост, частоИзображаетсяНа, открытки Санкт-Петербурга]
-
A.
commonlyDepictedOn
chosen
Indicates that something is frequently shown or represented on the surface, medium, or context of another thing.
-
B.
imageDepictedIn
Indicates that a particular image is shown, represented, or included within another resource or context.
-
C.
isDepictedVia
Indicates that one entity is represented, illustrated, or shown by means of another entity, such as a specific medium, style, or method of depiction.
-
D.
representedInPartBy
Indicates that something is partially depicted, expressed, or captured within another thing, but not in its entirety.
-
E.
imageDepictedWith
Indicates that one entity is visually represented together with another entity within the same image.
- 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_69f76e4b1f748190a380696a16eae4a2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.