Triple

T10076868
Position Surface form Disambiguated ID Type / Status
Subject Tom Wright E213786 entity
Predicate worksAt P7 FINISHED
Object WKK Architects E839314 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: WKK Architects | Statement: [Tom Wright, worksAt, WKK Architects]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WKK Architects
Context triple: [Tom Wright, worksAt, WKK Architects]
  • A. WKK Architects chosen
    WKK Architects is an architectural firm co-founded by Tom Wright, known for innovative and high-profile contemporary building designs.
  • B. JDS Architects
    JDS Architects is an international architecture and design firm known for innovative, sculptural projects such as the redevelopment of Oslo’s Holmenkollen ski arena.
  • C. TAK Architects
    TAK Architects is an architectural firm known for designing large-scale, high-profile projects such as the Meydan Racecourse in Dubai.
  • D. Bora Architects
    Bora Architects is a Portland-based architecture firm known for designing innovative cultural, educational, and civic spaces such as the Mesa Arts Center.
  • E. Kengo Kuma and Associates
    Kengo Kuma and Associates is a renowned Japanese architectural firm led by Kengo Kuma, celebrated for its innovative, nature-integrated designs and extensive use of traditional materials like wood.
  • 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd02f47e08190bfeb641b202beecc completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b649b7488190ad765d4ee6eac5d7 completed April 5, 2026, 7:21 p.m.
Created at: March 30, 2026, 8:59 p.m.