Triple

T15110626
Position Surface form Disambiguated ID Type / Status
Subject Brattleboro Literary Festival E360900 entity
Predicate hasSocialMedia P20647 FINISHED
Object Twitter E3345 NE FINISHED

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: Twitter | Statement: [Brattleboro Literary Festival, hasSocialMedia, Twitter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Twitter
Context triple: [Brattleboro Literary Festival, hasSocialMedia, 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. 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.
  • D. Weibo
    Weibo is a major Chinese microblogging and social media platform widely used for news, entertainment, and public discourse.
  • E. Instagram
    Instagram is a popular photo and video sharing social media platform known for its visual content, stories, and influencer culture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0058c04f481909deeac0271d961b6 completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7eb139c8190b76393e4a8be576b completed May 9, 2026, 4:28 a.m.
Created at: April 10, 2026, 3:05 a.m.