Triple

T3771123
Position Surface form Disambiguated ID Type / Status
Subject West Side E83199 entity
Predicate partOf P40 FINISHED
Object Disney Springs E11634 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: Disney Springs | Statement: [West Side, partOf, Disney Springs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Disney Springs
Context triple: [West Side, partOf, Disney Springs]
  • A. Disney Springs chosen
    Disney Springs is an outdoor shopping, dining, and entertainment complex at the Walt Disney World Resort in Florida.
  • B. Disneytown
    Disneytown is an outdoor shopping, dining, and entertainment district adjacent to Shanghai Disneyland, featuring themed restaurants, retail stores, and live performances.
  • C. Walt Disney World Resort
    Walt Disney World Resort is a massive entertainment complex near Orlando known for its theme parks, resorts, and attractions operated by The Walt Disney Company.
  • D. Downtown Disney
    Downtown Disney is an outdoor shopping, dining, and entertainment district located adjacent to the Disneyland Resort in Anaheim, California.
  • E. Epcot Resort Area
    The Epcot Resort Area is a collection of themed hotels, entertainment, and dining venues located around Crescent Lake near Epcot at Walt Disney World Resort in Florida.
  • 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_69ad8b235e608190b5a2b1d1bfcef50b completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcc307cf8819090730b5e697bb197 completed March 8, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69bb60d49ba08190b954fedd4c7bef5f completed March 19, 2026, 2:35 a.m.
Created at: March 8, 2026, 3:36 p.m.