Triple
T1447373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Twitch |
E31206
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | YouTube Live |
E2481
|
NE 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: YouTube Live | Statement: [Twitch, competitor, YouTube Live]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: YouTube Live Context triple: [Twitch, competitor, YouTube Live]
-
A.
Twitch
Twitch is a leading live-streaming platform, best known for video game broadcasting, esports coverage, and interactive content communities.
-
B.
Tank Stream
Tank Stream is a historic watercourse in central Sydney that once served as the colony’s primary freshwater supply and now runs mostly underground beneath the modern city.
-
C.
YouTube Studio
YouTube Studio is YouTube’s creator dashboard and management platform for uploading videos, tracking analytics, and managing channels.
-
D.
YouTube
chosen
YouTube is a global online video-sharing and streaming platform where users can upload, watch, and interact with a vast range of video content.
-
E.
Zoom Video Webinars
Zoom Video Webinars is a virtual event platform from Zoom that enables hosts to broadcast interactive, large-scale online presentations and seminars to remote audiences.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a499171a28819085b993a3ac78e363 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c55aa7dc8190aa7452d80ec8305e |
completed | March 1, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad08c229808190af9936b481390170 |
completed | March 8, 2026, 5:27 a.m. |
Created at: March 1, 2026, 8 p.m.