Triple

T412217
Position Surface form Disambiguated ID Type / Status
Subject Snap Inc. E9513 entity
Predicate develops P73 FINISHED
Object 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.
 E52239 NE FINISHED

How this triple was built (4 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: Bitmoji | Statement: [Snap Inc., develops, Bitmoji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bitmoji
Context triple: [Snap Inc., develops, Bitmoji]
  • A. Pixel
    Pixel is Google's flagship line of Android smartphones known for their clean software experience and advanced camera capabilities.
  • B. Tikkana
    Tikkana was a prominent 13th-century Telugu poet and scholar best known for translating a major portion of the Mahabharata into Telugu and helping shape classical Telugu literature.
  • C. Nokki
    Nokki is one of the four snow owl mascots created to represent the 1998 Winter Olympics held in Nagano, Japan.
  • D. Jamie
    Jamie is a given name commonly used as a diminutive or variant of James, and is borne by people of all genders in English-speaking countries.
  • E. JoyLabz
    JoyLabz is the company best known for creating the Makey Makey invention kit, which turns everyday objects into touchpads for creative, educational electronics projects.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bitmoji
Triple: [Snap Inc., develops, Bitmoji]
Generated description
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.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bitmoji
Target entity description: 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.
  • A. Pixel
    Pixel is Google's flagship line of Android smartphones known for their clean software experience and advanced camera capabilities.
  • B. Tikkana
    Tikkana was a prominent 13th-century Telugu poet and scholar best known for translating a major portion of the Mahabharata into Telugu and helping shape classical Telugu literature.
  • C. Nokki
    Nokki is one of the four snow owl mascots created to represent the 1998 Winter Olympics held in Nagano, Japan.
  • D. Jamie
    Jamie is a given name commonly used as a diminutive or variant of James, and is borne by people of all genders in English-speaking countries.
  • E. JoyLabz
    JoyLabz is the company best known for creating the Makey Makey invention kit, which turns everyday objects into touchpads for creative, educational electronics projects.
  • F. None of above. chosen

Provenance (5 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ecdafa2481908111accc918ff2e8 completed Feb. 28, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a41b49b5e48190b7b4a0cc21bb62d5 completed March 1, 2026, 10:56 a.m.
NEDg Description generation batch_69a41bafe9508190b5e3486bdac5d594 completed March 1, 2026, 10:57 a.m.
NED2 Entity disambiguation (via description) batch_69a41dabbcf4819084cbe8562d254c2b completed March 1, 2026, 11:06 a.m.
Created at: Feb. 28, 2026, 1:09 p.m.