Triple
T9844843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yuri Milner |
E239313
|
entity |
| Predicate | investedIn |
P17330
|
FINISHED |
| Object |
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 | Statement: [Yuri Milner, investedIn, WhatsApp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WhatsApp Context triple: [Yuri Milner, investedIn, 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 (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_69ca84e3f0c48190ada72a65ebd50efd |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb35dc29c819080203be5b904dc9d |
completed | April 2, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5dda4b0819092703270e87bee5a |
completed | April 5, 2026, 3:24 a.m. |
Created at: March 30, 2026, 8:33 p.m.