Triple

T16542502
Position Surface form Disambiguated ID Type / Status
Subject Swire Properties E401853 entity
Predicate brand P1500 FINISHED
Object Cityplaza E873775 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: Cityplaza | Statement: [Swire Properties, brand, Cityplaza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cityplaza
Context triple: [Swire Properties, brand, Cityplaza]
  • A. Cityplaza chosen
    Cityplaza is a major shopping and commercial complex in Hong Kong known for its extensive retail, dining, and entertainment offerings.
  • B. Cityplaza Three
    Cityplaza Three is one of the office tower components of the Cityplaza mixed-use complex in Hong Kong.
  • C. Central Plaza
    Central Plaza is the main ceremonial and civic square at the ancient Maya city of Calakmul, surrounded by prominent pyramids and public buildings that formed the core of its urban and ritual life.
  • D. Central Plaza
    Central Plaza is a prominent 78-story skyscraper in Hong Kong’s Wan Chai district, notable for its distinctive triangular floor plan and once holding the title of the city’s tallest building.
  • E. Central Plaza
    Central Plaza is the iconic hub at Disneyland where Main Street, U.S.A. meets the pathways to the park’s themed lands, centered around a view of Sleeping Beauty Castle.
  • 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3455db6788190b929546050ea2488 completed April 18, 2026, 8:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067b0e5708190a286b8a316d6efd2 completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 5:15 a.m.