Triple

T4951686
Position Surface form Disambiguated ID Type / Status
Subject #BalDiwas E111182 entity
Predicate platformUsedOn P28726 FINISHED
Object Twitter E3345 NE FINISHED

How this triple was built (3 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: Twitter | Statement: [#BalDiwas, platformUsedOn, Twitter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Twitter
Context triple: [#BalDiwas, platformUsedOn, Twitter]
  • A. Tweeter
    Tweeter is a fictional character from the Traveling Wilburys’ song “Tweeter and the Monkey Man,” depicted as a small-time criminal entangled in a noir-style tale of crime and betrayal.
  • B. Twitter, Inc. chosen
    Twitter, Inc. was a major social media and microblogging company best known for its real-time short-message platform that shaped online news, politics, and public discourse worldwide.
  • C. Weibo
    Weibo is a major Chinese microblogging and social media platform widely used for news, entertainment, and public discourse.
  • D. Instagram
    Instagram is a popular photo and video sharing social media platform known for its visual content, stories, and influencer culture.
  • E. Facebook
    Facebook is a major global social networking platform that allows users to connect, share content, and communicate online.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: platformUsedOn
Context triple: [#BalDiwas, platformUsedOn, Twitter]
  • A. platformUsed chosen
    Indicates that an action, event, or interaction was carried out using a particular platform (e.g., software, service, or system) as the medium or tool.
  • B. platformUsage
    Indicates how an entity uses, engages with, or relies on a particular platform for its activities or services.
  • C. platformName
    Indicates the name or identifier of the platform associated with the entity or action.
  • D. typicalPlatform
    Indicates that something commonly or usually serves as the platform or environment on which another thing operates, appears, or is based.
  • E. platformIncludes
    Indicates that a platform contains, supports, or provides access to the specified component, feature, or content.
  • F. None of above.

Provenance (4 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_69bd4418390c8190b7e9766a2512ce55 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71b561ec81908083225269222e96 completed March 20, 2026, 4:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69be81d3d9548190ae0a34549eb88036 completed March 21, 2026, 11:32 a.m.
PD Predicate disambiguation batch_69bd6c3aa1388190b3e0c8ee1ba1e4fa completed March 20, 2026, 3:48 p.m.
Created at: March 20, 2026, 1:31 p.m.