Triple

T1682750
Position Surface form Disambiguated ID Type / Status
Subject IGTV E36372 entity
Predicate competedWith P1375 FINISHED
Object Snapchat Discover E52237 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: Snapchat Discover | Statement: [IGTV, competedWith, Snapchat Discover]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Snapchat Discover
Context triple: [IGTV, competedWith, Snapchat Discover]
  • A. Snapchat chosen
    Snapchat is a multimedia messaging and social media app known for its disappearing photos and videos, creative filters, and Stories feature popular among younger users.
  • B. Periscope
    Periscope was a live video streaming mobile app that allowed users to broadcast and watch real-time video from around the world.
  • C. TikTok
    TikTok is a popular short-form video-sharing platform known for its algorithm-driven content feed, viral trends, and user-generated music and dance videos.
  • D. Instagram Reels
    Instagram Reels is a short-form video feature within Instagram that lets users create, edit, and share brief, often music-backed clips for discovery and entertainment.
  • E. iDiscover
    iDiscover is the online search and discovery platform used to access Cambridge University’s library collections, including books, journals, and electronic resources.
  • 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_69a886139ed081909af0940aa9313512 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa627ab38081909d5f264ca49e036a completed March 6, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad71bf1998819094d3eb67c6e6bafd completed March 8, 2026, 12:55 p.m.
Created at: March 4, 2026, 7:29 p.m.