Triple

T15717185
Position Surface form Disambiguated ID Type / Status
Subject Sony Building E380991 entity
Predicate formerName P65 FINISHED
Object Sony Tower E78545 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: Sony Tower | Statement: [Sony Building, formerName, Sony Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sony Tower
Context triple: [Sony Building, formerName, Sony Tower]
  • A. Sony Tower chosen
    Sony Tower is a prominent postmodern skyscraper in Midtown Manhattan, New York City, renowned for its distinctive Chippendale-style broken pediment top.
  • B. Lotte World Tower
    Lotte World Tower is a 123-story supertall skyscraper in Seoul that ranks among the tallest buildings in the world and serves as a major commercial, cultural, and tourist hub.
  • C. Posco Tower Seoul
    Posco Tower Seoul is a prominent skyscraper and corporate office building in Seoul, South Korea, serving as a major landmark and business hub in the city.
  • D. Mirae Asset Tower
    Mirae Asset Tower is a prominent modern skyscraper in Shanghai’s Pudong financial district, contributing to the iconic skyline along the Huangpu River.
  • E. Seoul Station City Tower
    Seoul Station City Tower is a prominent high-rise commercial complex in Seoul, South Korea, designed by the international architecture firm Kohn Pedersen Fox.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f91beb08190bd91bf9306737c3b completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff7583609c8190a80421fce649900f completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:45 a.m.