Triple

T3419521
Position Surface form Disambiguated ID Type / Status
Subject WhatsApp E72083 entity
Predicate supportsFeature P203 FINISHED
Object WhatsApp Web E72083 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: WhatsApp Web | Statement: [WhatsApp, supportsFeature, WhatsApp Web]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WhatsApp Web
Context triple: [WhatsApp, supportsFeature, WhatsApp Web]
  • A. WhatsApp chosen
    WhatsApp is a widely used cross-platform messaging application that allows users to send text, voice, and multimedia messages and make voice and video calls over the internet.
  • B. WeChat
    WeChat is a Chinese multi-purpose mobile app developed by Tencent that combines messaging, social media, and payment services into a single platform.
  • C. Google Duo
    Google Duo is a high-quality video and voice calling app developed by Google for simple, reliable one-to-one and group communication across mobile and web platforms.
  • D. Telegram
    Telegram is a cloud-based instant messaging service known for its speed, security features, and support for large group chats and channels across multiple platforms.
  • E. Facebook Chat
    Facebook Chat is the instant messaging feature of the Facebook platform that allows users to send real-time text messages and multimedia to their Facebook contacts.
  • 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_69ad85ad38e48190b7660c5118a35289 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb94d6808819080997df30119e71e completed March 8, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69b354701e908190a8a7f14ae578fa5d completed March 13, 2026, 12:04 a.m.
Created at: March 8, 2026, 3:15 p.m.