Triple

T7537321
Position Surface form Disambiguated ID Type / Status
Subject David Duke E178181 entity
Predicate hasBeenBannedFrom P24172 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: [David Duke, hasBeenBannedFrom, Twitter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Twitter
Context triple: [David Duke, hasBeenBannedFrom, 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: hasBeenBannedFrom
Context triple: [David Duke, hasBeenBannedFrom, Twitter]
  • A. bannedAfter
    Indicates that one entity becomes prohibited or forbidden only after the occurrence or establishment of another specified entity or event.
  • B. bannedBy
    Indicates that an entity is prohibited or disallowed as a result of a decision or action taken by another entity.
  • C. hasJetBan
    Indicates that an entity is subject to a prohibition or restriction on the use or operation of jet aircraft.
  • D. wasBlacklisted chosen
    Indicates that an entity has been officially banned or excluded from participation, access, or consideration, typically due to disapproval or violation of rules.
  • E. reasonForBan
    Indicates the justification or cause that led to an entity being banned.
  • 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_69c69f2be3888190a6667a27f8f195e9 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f84db0c48190b2b3d8c5f802f713 completed March 27, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84f108aec81909b0738b6273d5bd3 completed March 28, 2026, 9:58 p.m.
PD Predicate disambiguation batch_69c6f4d8eedc81908c1ae421e0e63798 completed March 27, 2026, 9:21 p.m.
Created at: March 27, 2026, 3:48 p.m.