Triple

T7728210
Position Surface form Disambiguated ID Type / Status
Subject Ma Yansong E175184 entity
Predicate employer P7 FINISHED
Object MAD Architects E658707 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: MAD Architects | Statement: [Ma Yansong, employer, MAD Architects]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MAD Architects
Context triple: [Ma Yansong, employer, MAD Architects]
  • A. MAD Architects chosen
    MAD Architects is a Beijing-based architecture firm known for its futuristic, organic high-rise designs and large-scale urban projects around the world.
  • B. Zaha Hadid Architects
    Zaha Hadid Architects is a globally renowned architecture firm known for its futuristic, fluid designs and landmark projects around the world.
  • C. Safdie Architects
    Safdie Architects is an international architecture and urban design firm renowned for its innovative, human-centered projects that often integrate nature and bold geometric forms.
  • D. SHoP Architects
    SHoP Architects is a New York–based architecture firm known for its innovative, technologically driven designs and prominent urban projects, including major cultural and mixed-use developments.
  • E. Morphosis Architects
    Morphosis Architects is an innovative American architecture firm known for its avant-garde, high-tech designs and complex, sculptural buildings worldwide.
  • 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_69c6995e912c81909a49a2657103f786 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70315e8e88190a5c7e5d2f2ef66bc completed March 27, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be3244088190be26dec90db9cfb3 completed March 29, 2026, 5:52 a.m.
Created at: March 27, 2026, 4:06 p.m.