Triple
T575634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | YouTube Studio |
E13755
|
entity |
| Predicate | accessibleFromURL |
P6055
|
FINISHED |
| Object | https://studio.youtube.com |
—
|
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: https://studio.youtube.com | Statement: [YouTube Studio, accessibleFromURL, https://studio.youtube.com]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessibleFromURL Context triple: [YouTube Studio, accessibleFromURL, https://studio.youtube.com]
-
A.
accessibleFrom
Indicates that one entity can be reached, entered, or used starting from another entity, typically without obstruction.
-
B.
accessURL
chosen
Indicates the web address or endpoint through which a resource can be accessed or retrieved.
-
C.
notAccessibleBy
Indicates that one entity cannot be reached, used, or obtained through another specified entity or means.
-
D.
canRefer
Indicates that one entity has the ability or permission to mention, point to, or direct attention to another entity.
-
E.
accessible
Indicates that one entity can be reached, entered, used, or understood by another entity, often without undue difficulty or barriers.
- 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_69a4933fa4d88190a7949cc83c08c5c1 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b67395c8190a8046ff7debe9d1f |
completed | March 1, 2026, 8:02 p.m. |
| PD | Predicate disambiguation | batch_69a494c4969c819080375d08f9eec50c |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.