Triple
T9431789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | StumbleUpon |
E227393
|
entity |
| Predicate | successorPlatformURL |
P81857
|
FINISHED |
| Object | https://mix.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://mix.com | Statement: [StumbleUpon, successorPlatformURL, https://mix.com]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorPlatformURL Context triple: [StumbleUpon, successorPlatformURL, https://mix.com]
-
A.
laterPlatform
Indicates that one entity occurs, appears, or is positioned on a platform that comes after another platform in time or sequence.
-
B.
launchPlatformName
Indicates the name of the platform or site from which a launch (typically of a vehicle, rocket, or mission) is conducted.
-
C.
launchPlatformFor
Indicates a relationship where one entity serves as the platform or site from which another entity is launched.
-
D.
announcedPlatform
Indicates that an entity has publicly revealed or introduced a particular platform (such as a system, service, or technology).
-
E.
sequelPlatform
chosen
Indicates that one platform is a follow-up or successor to another platform in a series or progression.
- 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_69ca8437a7ac81908651de48f2d2141d |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7e6059bc8190a7e98aef3caabd0b |
completed | April 1, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69cca55548488190b171ae695a3212de |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:49 p.m.