Triple
T9101040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prospekt Vernadskogo |
E218152
|
entity |
| Predicate | platformSurface |
P58186
|
FINISHED |
| Object | granite |
—
|
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: granite | Statement: [Prospekt Vernadskogo, platformSurface, granite]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformSurface Context triple: [Prospekt Vernadskogo, platformSurface, granite]
-
A.
usesSurface
chosen
Indicates that one entity employs or interacts with another entity as a surface or platform for its action or function.
-
B.
surfaceAccess
Indicates that one entity provides a means for another entity to reach, enter, or interact with a surface or outer layer.
-
C.
surfaceState
Indicates the physical condition or status of a surface, such as its texture, cleanliness, damage, or treatment at a given time.
-
D.
playsOnSurface
Indicates that an entity performs or engages in an activity while being in contact with or supported by a particular surface.
-
E.
platformAppearance
Indicates how an entity is visually presented or styled on a particular platform or interface.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9711babc8190a336812dd08d9c73 |
completed | April 1, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:15 p.m.