Triple
T21933268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sneak Previews |
E541623
|
entity |
| Predicate | hasReviewScale |
P59739
|
FINISHED |
| Object | thumbs up |
—
|
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: thumbs up | Statement: [Sneak Previews, hasReviewScale, thumbs up]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReviewScale Context triple: [Sneak Previews, hasReviewScale, thumbs up]
-
A.
hasRecension
Indicates that one textual version or edition is a revised or alternative form of another text.
-
B.
hasRatingLevel
chosen
Indicates that an entity is associated with a particular rating level or score category.
-
C.
hasReviewReception
Indicates that an entity has received a critical or evaluative review describing how it was received or perceived.
-
D.
hasReviewBody
Indicates that an entity has an associated textual review content or body describing an evaluation or opinion about it.
-
E.
usesRating
Indicates that one entity applies, relies on, or incorporates a rating assigned to another entity.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12400a1248190b3f8f27f2aa4a858 |
completed | April 28, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:47 p.m.