Triple
T17676738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Stadia |
E440658
|
entity |
| Predicate | minimumRecommendedBandwidth |
P81510
|
FINISHED |
| Object | 10 Mbps |
—
|
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: 10 Mbps | Statement: [Google Stadia, minimumRecommendedBandwidth, 10 Mbps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumRecommendedBandwidth Context triple: [Google Stadia, minimumRecommendedBandwidth, 10 Mbps]
-
A.
lowerBandWidth
Indicates that one entity has a smaller or more limited bandwidth capacity than another.
-
B.
supportsBandwidths
Indicates that an entity is compatible with or can operate using the specified range or set of bandwidth values.
-
C.
minimumWidth
Indicates that there is a specified smallest allowable or required width for something in the relationship.
-
D.
recommendedMinimumSize
chosen
Indicates the smallest size that is advised or suggested as a minimum for something to be used or considered appropriate.
-
E.
usesChannelBandwidth
Indicates that one entity consumes or occupies a portion of the available bandwidth on a communication channel.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f6d9ab88190ab0e25eac8b0101c |
completed | April 19, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_69e3cde007d8819090dd92eea9f022cc |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 10:01 a.m.