Triple

T4378900
Position Surface form Disambiguated ID Type / Status
Subject Arsenal Yards E99078 entity
Predicate formerNameOfSite P65 FINISHED
Object Arsenal Mall E435738 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: Arsenal Mall | Statement: [Arsenal Yards, formerNameOfSite, Arsenal Mall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arsenal Mall
Context triple: [Arsenal Yards, formerNameOfSite, Arsenal Mall]
  • A. Arsenal Mall chosen
    Arsenal Mall was a former shopping center in Watertown, Massachusetts that has been redeveloped into the mixed-use complex now known as Arsenal Yards.
  • B. Fairview Mall
    Fairview Mall is a large shopping centre in Toronto, Ontario, featuring a wide range of retail stores, dining options, and services.
  • C. Southridge Mall
    Southridge Mall is a major regional shopping center located in Greendale, Wisconsin, featuring a wide variety of retail stores, dining options, and services.
  • D. County Mall
    County Mall is a major shopping centre in Crawley, West Sussex, featuring a wide range of retail stores, eateries, and services.
  • E. Greenbelt Mall
    Greenbelt Mall is a local shopping center in Greenbelt, Maryland, offering a variety of retail stores and services to the surrounding community.
  • 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: formerNameOfSite
Context triple: [Arsenal Yards, formerNameOfSite, Arsenal Mall]
  • A. formerSiteOf
    Indicates that a location previously hosted or contained something (such as a structure, organization, or event) that is no longer present there.
  • B. formerName chosen
    Indicates that an entity was previously known by a different name in the past.
  • C. formerUrl
    Indicates that one entity was previously identified or accessible via the URL represented by the other entity, but that URL is no longer current.
  • D. formerOrganization
    Indicates that an entity was previously affiliated with or employed by a given organization, but is no longer associated with it.
  • E. formerNameOfCapital
    Indicates that one entity was the previous official name of a capital city before it was renamed.
  • 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_69b3454ea8f48190a49c2436624d6ef6 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35240092c81908e26ff607d665e7a completed March 12, 2026, 11:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5f5e210108190bf14731ce3774b6b completed March 14, 2026, 11:57 p.m.
PD Predicate disambiguation batch_69b34f557fe8819085032bf7f0cea5dc completed March 12, 2026, 11:42 p.m.
Created at: March 12, 2026, 11:18 p.m.