Triple

T2646783
Position Surface form Disambiguated ID Type / Status
Subject Dom Square E53802 entity
Predicate hasViewOf P854 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: [Dom Square, hasViewOf, Dom Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dom Tower
Context triple: [Dom Square, hasViewOf, 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. Leland Tower
    Leland Tower is a historic high-rise building in downtown Aurora, Illinois, once the tallest building in the state outside Chicago and a prominent local landmark.
  • D. Hilton Tower
    Hilton Tower is the common name for Beetham Tower, a prominent mixed-use skyscraper and landmark on Manchester’s skyline.
  • E. Marathon Tower
    Marathon Tower was a prominent architectural feature of the 1928 Amsterdam Olympic Stadium, serving as a symbolic focal point for the Games and the marathon event.
  • 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd919bf2c81908feb768f3391e985 completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa050cc408190b2fa81a0f2da06eb completed March 10, 2026, 4:38 a.m.
Created at: March 6, 2026, 9:53 p.m.