Triple
T38376461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Velká Deštná observation tower |
E893633
|
entity |
| Predicate | hasViewRange |
P854
|
FINISHED |
| Object | panoramic 360-degree view |
—
|
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: panoramic 360-degree view | Statement: [Velká Deštná observation tower, hasViewRange, panoramic 360-degree view]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasViewRange Context triple: [Velká Deštná observation tower, hasViewRange, panoramic 360-degree view]
-
A.
hasView
chosen
Indicates that one entity provides a visual perspective or outlook onto another entity or scene.
-
B.
hasRange
Indicates that a property or relation is constrained to take its values from a specified class, type, or value set.
-
C.
hasParticularView
Indicates that one entity holds, expresses, or is characterized by a specific opinion, perspective, or standpoint regarding something.
-
D.
hasPageRange
Indicates that one entity (such as a document section or article) spans a specific, continuous range of pages in another entity (such as a publication or volume).
-
E.
hasViewThrough
Indicates that one entity can be seen or visually perceived through another entity acting as an intermediate medium or opening.
- 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_69fde5d7d9548190880a9d95b8f0f66b |
completed | May 8, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69fde4e1bf9c81909754545275eccc03 |
completed | May 8, 2026, 1:28 p.m. |
Created at: May 3, 2026, 4:31 p.m.