Triple
T10120384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commonwealth Games men's doubles |
E223270
|
entity |
| Predicate | videoReviewSystem |
P92083
|
FINISHED |
| Object | may use instant review system in recent editions |
—
|
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: may use instant review system in recent editions | Statement: [Commonwealth Games men's doubles, videoReviewSystem, may use instant review system in recent editions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: videoReviewSystem Context triple: [Commonwealth Games men's doubles, videoReviewSystem, may use instant review system in recent editions]
-
A.
reviewOf
Indicates that one entity is a critical or evaluative assessment that is about or directed toward another entity.
-
B.
reviewType
Indicates the specific category or kind of review associated with an item, action, or relationship.
-
C.
ratingSystem
Indicates a system or method used to assign evaluative scores or rankings to items, actions, or entities based on defined criteria.
-
D.
hasRecension
Indicates that one textual version or edition is a revised or alternative form of another text.
-
E.
reviewAggregator
Indicates that an entity functions as a collector and summarizer of reviews or ratings about other entities.
- F. None of above. chosen
Provenance (4 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2659cdc8190b3ba91426bda55ec |
completed | April 2, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba1d360819087698d04a53cc87e |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd4fed19d481909d2c7ff1114664b6 |
completed | April 1, 2026, 5:03 p.m. |
Created at: March 30, 2026, 9:04 p.m.