Triple

T12569003
Position Surface form Disambiguated ID Type / Status
Subject Domstraat E295549 entity
Predicate near P350 FINISHED
Object Dom Tower E285137 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: Dom Tower | Statement: [Domstraat, near, Dom Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dom Tower
Context triple: [Domstraat, near, Dom Tower]
  • A. Dom Tower chosen
    Dom Tower is the iconic medieval church tower of Utrecht in the Netherlands, renowned as the country’s tallest and a prominent symbol of the city.
  • B. Terminal Tower
    Terminal Tower is a historic skyscraper in downtown Cleveland, Ohio, that long served as a major office building and transportation hub and was once one of the tallest buildings in the world.
  • C. Republic Tower
    Republic Tower is a prominent high-rise residential building in Melbourne, Australia, recognized for its distinctive contemporary design by Fender Katsalidis Architects.
  • D. Tower 185
    Tower 185 is a prominent high-rise office building in Frankfurt am Main, Germany, known for its distinctive architecture and role in shaping the city’s modern financial district skyline.
  • E. Gatliff Tower
    Gatliff Tower is a residential high-rise block located within the World’s End Estate in Chelsea, London.
  • 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d954a325948190994bcfc9d571a3a8 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6559336088190874123c06c86630e completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 11:50 p.m.