Triple

T18258066
Position Surface form Disambiguated ID Type / Status
Subject Path E437266 entity
Predicate competitor P1375 FINISHED
Object WhatsApp NE NERFINISHED

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 | Statement: [Path, competitor, WhatsApp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WhatsApp
Context triple: [Path, competitor, WhatsApp]
  • 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. Viber
    Viber is a cross-platform messaging and Voice over IP (VoIP) application that allows users to send messages, make voice and video calls, and share media over the internet.
  • C. WeChat
    WeChat is a Chinese multi-purpose mobile app developed by Tencent that combines messaging, social media, and payment services into a single platform.
  • D. 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.
  • E. Skype
    Skype is a widely used internet-based communication service that enables voice calls, video chats, and instant messaging across computers and mobile devices.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4fd8879e88190893f8da7c3529496 completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 10:34 a.m.