Triple
T38377836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дворцовый мост |
E893673
|
entity |
| Predicate | материалПролётныхСтроений |
P52395
|
FINISHED |
| Object | сталь |
—
|
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: сталь | Statement: [Дворцовый мост, материалПролётныхСтроений, сталь]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: материалПролётныхСтроений Context triple: [Дворцовый мост, материалПролётныхСтроений, сталь]
-
A.
bridgeStructure
Indicates a structural relationship where one entity functions as a bridge that spans or connects two separate points or areas.
-
B.
bridgeMaterial
chosen
Indicates that a bridge is constructed from, or primarily composed of, a specified material.
-
C.
architecturalElements
Indicates a relationship where certain components or features function as structural or design elements within an architectural context.
-
D.
hasBridgeOrStructure
Indicates that there exists a bridge or similar structural connection between the related entities.
-
E.
مادة البناء
Indicates a relationship where something serves as, or is used as, a construction material in building or structural work.
- 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_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.