Triple

T146686
Position Surface form Disambiguated ID Type / Status
Subject Twitter, Inc. E3345 entity
Predicate operated P1688 FINISHED
Object Periscope
Periscope was a live video streaming mobile app that allowed users to broadcast and watch real-time video from around the world.
E17428 NE FINISHED

How this triple was built (4 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: Periscope | Statement: [Twitter, Inc., operated, Periscope]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Periscope
Context triple: [Twitter, Inc., operated, Periscope]
  • A. Blink
    Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
  • B. Snap Inc.
    Snap Inc. is an American technology and social media company best known for developing the multimedia messaging app Snapchat and related camera and augmented reality products.
  • C. BARD Mobile app
    The BARD Mobile app is a specialized application that provides accessible audio and braille books and magazines to people who are blind, visually impaired, or print disabled.
  • D. Optica
    Optica is a leading scientific society dedicated to advancing the study and application of optics and photonics worldwide.
  • E. YouTube
    YouTube is a global online video-sharing and streaming platform where users can upload, watch, and interact with a vast range of video content.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Periscope
Triple: [Twitter, Inc., operated, Periscope]
Generated description
Periscope was a live video streaming mobile app that allowed users to broadcast and watch real-time video from around the world.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Periscope
Target entity description: Periscope was a live video streaming mobile app that allowed users to broadcast and watch real-time video from around the world.
  • A. Blink
    Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
  • B. Snap Inc.
    Snap Inc. is an American technology and social media company best known for developing the multimedia messaging app Snapchat and related camera and augmented reality products.
  • C. BARD Mobile app
    The BARD Mobile app is a specialized application that provides accessible audio and braille books and magazines to people who are blind, visually impaired, or print disabled.
  • D. Optica
    Optica is a leading scientific society dedicated to advancing the study and application of optics and photonics worldwide.
  • E. YouTube
    YouTube is a global online video-sharing and streaming platform where users can upload, watch, and interact with a vast range of video content.
  • F. None of above. chosen

Provenance (5 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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a25bab43608190ba5ebfbee6b5b6e4 completed Feb. 28, 2026, 3:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2c2763ce481908c12046de9003a84 completed Feb. 28, 2026, 10:24 a.m.
NEDg Description generation batch_69a2c2f02810819092e3263ac91b5fe3 completed Feb. 28, 2026, 10:26 a.m.
NED2 Entity disambiguation (via description) batch_69a2c369498481908c4213b04aea9c97 completed Feb. 28, 2026, 10:28 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.