Triple
T33578359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Britain's Got Talent audition performance of "I Dreamed a Dream" |
E860086
|
entity |
| Predicate | viewCountDescription |
P124009
|
FINISHED |
| Object | tens of millions of views within weeks |
—
|
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: tens of millions of views within weeks | Statement: [Britain's Got Talent audition performance of "I Dreamed a Dream", viewCountDescription, tens of millions of views within weeks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewCountDescription Context triple: [Britain's Got Talent audition performance of "I Dreamed a Dream", viewCountDescription, tens of millions of views within weeks]
-
A.
viewCount
chosen
Indicates the number of times something has been viewed or accessed.
-
B.
viewCountMilestoneDate
Indicates the date on which a specific view-count milestone was reached for the associated item or content.
-
C.
previewCount
Indicates the number of times an item has been previewed or viewed in a preliminary or sample form.
-
D.
viewedBy
Indicates that something has been seen, observed, or watched by a particular entity.
-
E.
bookmarkCount
Indicates the number of times an item has been bookmarked by users.
- 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_69f3497d37848190afcbb5ef3f5c7376 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f76e085c81909d71d6f47853cd12 |
completed | May 3, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:40 a.m.