Triple

T20221254
Position Surface form Disambiguated ID Type / Status
Subject Apple WWDC 2018 E495259 entity
Predicate announced P429 FINISHED
Object Memoji 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: Memoji | Statement: [Apple WWDC 2018, announced, Memoji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Memoji
Context triple: [Apple WWDC 2018, announced, Memoji]
  • A. Bitmoji
    Bitmoji is a popular app and feature that lets users create personalized cartoon avatars and use them as expressive stickers across messaging and social platforms.
  • B. Animoji and Memoji chosen
    Animoji and Memoji are Apple’s animated, customizable characters that mirror a user’s facial expressions and are used in messaging and video calls on compatible Apple devices.
  • C. Moji
    Moji was a former city in Fukuoka Prefecture, Japan, that later became a ward of Kitakyushu and is known for its historic port and preserved retro district.
  • D. Timoji
    Timoji was a local privateer and military leader on the western coast of India who allied with the Portuguese and played a key role in their early 16th-century expansion in Goa.
  • E. Kik
    Kik is a mobile instant messaging app that allows users to chat, share media, and interact with bots and services through a username-based platform.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fd610f881908fdd22b1f8bd2efc completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.