Triple

T22035763
Position Surface form Disambiguated ID Type / Status
Subject @Raptors905 E544202 entity
Predicate formerPlatformName P113835 FINISHED
Object Twitter — NE NERFINISHED

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: [@Raptors905, formerPlatformName, Twitter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Twitter
Context triple: [@Raptors905, formerPlatformName, Twitter]
  • A. Tweet
    The Tweet is the nickname of the Cessna T-37, a small twin‑engine jet trainer aircraft used extensively by the U.S. Air Force and several other countries for pilot training.
  • B. 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.
  • C. Thuit
    Thuit is a locality in France known historically as the place where the 18th-century French chancellor René Nicolas Charles Augustin de Maupeou died.
  • D. 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.
  • E. Weibo
    Weibo is a major Chinese microblogging and social media platform widely used for news, entertainment, and public discourse.
  • 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: formerPlatformName
Context triple: [@Raptors905, formerPlatformName, Twitter]
  • A. formerName
    Indicates that an entity was previously known by a different name in the past.
  • B. formerDistributionPlatform chosen
    Indicates that an entity previously served as a distribution platform for another entity but no longer holds that role.
  • C. previousSystemName
    Indicates that an entity was formerly known by a different system name prior to its current designation.
  • D. formerBrand
    Indicates that an entity was previously used or recognized as a brand for another entity but is no longer its current brand.
  • E. formerDomain
    Indicates that one entity was previously the domain or area of control, influence, or ownership of another entity, but no longer is.
  • F. None of above.

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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127f1f95c8190a324c84313cd91ee completed April 28, 2026, 9:34 p.m.
PD Predicate disambiguation batch_69e6f63b0d048190b241622759aab9de completed April 21, 2026, 3:59 a.m.
Created at: April 16, 2026, 8:25 p.m.