Triple

T6459919
Position Surface form Disambiguated ID Type / Status
Subject Jelly E142090 entity
Predicate creatorPreviousAffiliation P9419 FINISHED
Object Twitter E3345 NE FINISHED

How this triple was built (3 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: Twitter | Statement: [Jelly, creatorPreviousAffiliation, Twitter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Twitter
Context triple: [Jelly, creatorPreviousAffiliation, Twitter]
  • A. Tweeter
    Tweeter is a fictional character from the Traveling Wilburys’ song “Tweeter and the Monkey Man,” depicted as a small-time criminal entangled in a noir-style tale of crime and betrayal.
  • B. Twitter, Inc. chosen
    Twitter, Inc. was a major social media and microblogging company best known for its real-time short-message platform that shaped online news, politics, and public discourse worldwide.
  • C. Weibo
    Weibo is a major Chinese microblogging and social media platform widely used for news, entertainment, and public discourse.
  • D. Instagram
    Instagram is a popular photo and video sharing social media platform known for its visual content, stories, and influencer culture.
  • E. Tweeter Center
    Tweeter Center was a former name of the large outdoor concert amphitheater now known as the Hollywood Casino Amphitheatre in Tinley Park, Illinois.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: creatorPreviousAffiliation
Context triple: [Jelly, creatorPreviousAffiliation, Twitter]
  • A. previousCorporateAffiliation
    Indicates that an entity was formerly employed by, associated with, or part of a specified corporate organization before its current status or affiliation.
  • B. hasFormerInstitution chosen
    Indicates that an entity was previously affiliated with, employed by, or enrolled in a particular institution in the past.
  • C. laterAffiliation
    Indicates that an entity becomes affiliated with another entity at a later time than a previously mentioned or initial affiliation.
  • D. formerAffiliationLevel
    Indicates that an entity previously held a specific level or status within an affiliation, but no longer does so.
  • E. formerEmployer
    Indicates that one entity previously employed the other but no longer does so.
  • F. None of above.

Provenance (4 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_69c008d2f91c8190a8178767a35e08fc completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069f50ea88190af29c8c249ff2b69 completed March 22, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bdc4e808190a7c24b963ab0aa30 completed March 27, 2026, 9:20 a.m.
PD Predicate disambiguation batch_69c0673b44148190aed70084f0ff4992 completed March 22, 2026, 10:03 p.m.
Created at: March 22, 2026, 4:48 p.m.