Triple

T708883
Position Surface form Disambiguated ID Type / Status
Subject Prague E14162 entity
Predicate hasLandmark P105 FINISHED
Object Dancing House E41822 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: Dancing House | Statement: [Prague, hasLandmark, Dancing House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dancing House
Context triple: [Prague, hasLandmark, Dancing House]
  • A. Dancing House chosen
    Dancing House is a famously deconstructivist, curving office building in Prague known for its dynamic, dancing-like silhouette designed by Frank Gehry and Vlado Milunić.
  • B. Renaissance Tower
    Renaissance Tower is a prominent modernist office skyscraper and one of the most recognizable landmarks in the Dallas, Texas skyline.
  • C. Gehry Tower
    Gehry Tower is a distinctive, deconstructivist-style stainless steel-clad building in Hanover, Germany, designed by renowned architect Frank Gehry.
  • D. Prague Castle
    Prague Castle is a historic fortress complex in Prague that served as the seat of Bohemian kings and Holy Roman Emperors and is now the official residence of the Czech president.
  • E. Fisherman's Bastion
    Fisherman's Bastion is a neo-Romanesque terrace and lookout in Budapest famed for its panoramic views over the Danube and the Hungarian Parliament.
  • 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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a548e6dc819090d31ce33493a396 completed March 1, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a654dcbb688190ab997a3d31ec729a completed March 3, 2026, 3:26 a.m.
Created at: March 1, 2026, 7:36 p.m.