Triple
T19536062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skeleton Clique |
E488768
|
entity |
| Predicate | activeOnPlatform |
P1292
|
FINISHED |
| Object | Discord |
—
|
NE NERFINISHED |
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: Discord | Statement: [Skeleton Clique, activeOnPlatform, Discord]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Discord Context triple: [Skeleton Clique, activeOnPlatform, Discord]
-
A.
Discord
chosen
Discord is a popular communication platform that provides text, voice, and video chat for online communities, gamers, and groups.
-
B.
Slack
Slack is a cloud-based team collaboration and messaging platform widely used for real-time communication, file sharing, and integrations with tools like Google Workspace.
-
C.
Mattermost
Mattermost is an open-source, self-hosted messaging and collaboration platform designed for secure team communication and integration with developer tools.
-
D.
Parler
Parler is a social media platform known for its emphasis on minimal content moderation and popularity among right-wing and conservative users.
-
E.
IRC
IRC is a global humanitarian organization that responds to crises by providing emergency aid, protection, and long-term support to refugees and displaced people.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6386f0fac819081bbc29172c8965e |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.