Triple

T15238118
Position Surface form Disambiguated ID Type / Status
Subject Xinyi District E364181 entity
Predicate contains P35 FINISHED
Object ATT 4 FUN
ATT 4 FUN is a popular multi-story shopping and entertainment complex in Taipei, Taiwan, known for its fashion boutiques, restaurants, and nightlife venues.
 E1145341 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: ATT 4 FUN | Statement: [Xinyi District, contains, ATT 4 FUN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ATT 4 FUN
Context triple: [Xinyi District, contains, ATT 4 FUN]
  • A. Fort Fun
    Fort Fun is a playful nickname for Fort Collins, Colorado, highlighting the city’s lively, recreation-focused atmosphere.
  • B. FUN!
    "FUN!" is a track by American rapper Vince Staples that showcases his sharp lyricism and darkly humorous commentary over an energetic, experimental production.
  • C. Funt
    Funt is a surname most notably associated with Allen Funt, the creator and host of the pioneering hidden-camera television show "Candid Camera."
  • D. Game for a Laugh
    Game for a Laugh was a popular British television practical-joke and hidden-camera show that aired in the 1980s, known for its light-hearted stunts and audience participation.
  • E. Love 4 Fun
    "Love 4 Fun" is a song featured on the album *Escape* by the Eurodance group E-Rotic.
  • 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: ATT 4 FUN
Triple: [Xinyi District, contains, ATT 4 FUN]
Generated description
ATT 4 FUN is a popular multi-story shopping and entertainment complex in Taipei, Taiwan, known for its fashion boutiques, restaurants, and nightlife venues.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ATT 4 FUN
Target entity description: ATT 4 FUN is a popular multi-story shopping and entertainment complex in Taipei, Taiwan, known for its fashion boutiques, restaurants, and nightlife venues.
  • A. Fort Fun
    Fort Fun is a playful nickname for Fort Collins, Colorado, highlighting the city’s lively, recreation-focused atmosphere.
  • B. FUN!
    "FUN!" is a track by American rapper Vince Staples that showcases his sharp lyricism and darkly humorous commentary over an energetic, experimental production.
  • C. Funt
    Funt is a surname most notably associated with Allen Funt, the creator and host of the pioneering hidden-camera television show "Candid Camera."
  • D. Game for a Laugh
    Game for a Laugh was a popular British television practical-joke and hidden-camera show that aired in the 1980s, known for its light-hearted stunts and audience participation.
  • E. Love 4 Fun
    "Love 4 Fun" is a song featured on the album *Escape* by the Eurodance group E-Rotic.
  • 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_69d85a0dde7481908fc64d1e82d5d20d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007da7e988190925a9b67b8070bc7 completed April 15, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd3f9d308190af5374f0362c62f5 completed May 9, 2026, 7:07 a.m.
NEDg Description generation batch_69feded546688190b931b60a55babcd0 completed May 9, 2026, 7:14 a.m.
NED2 Entity disambiguation (via description) batch_69fedf72e6148190afbfbe92ed2ed277 completed May 9, 2026, 7:17 a.m.
Created at: April 10, 2026, 3:12 a.m.