Triple

T10089873
Position Surface form Disambiguated ID Type / Status
Subject Andrea King E215313 entity
Predicate workedOn P3 FINISHED
Object Hotel Berlin E272482 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: Hotel Berlin | Statement: [Andrea King, workedOn, Hotel Berlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hotel Berlin
Context triple: [Andrea King, workedOn, Hotel Berlin]
  • A. Hotel Berlin chosen
    "Hotel Berlin" is a 1945 World War II–era drama film set in a luxury Berlin hotel during the final days of the Nazi regime, adapted from Vicki Baum’s novel of the same name.
  • B. Park Inn Berlin Alexanderplatz
    Park Inn Berlin Alexanderplatz is a high-rise hotel in central Berlin known for its prominent location on Alexanderplatz and panoramic city views.
  • C. Hotel Moskva
    Hotel Moskva is a historic and iconic luxury hotel in central Belgrade, renowned for its distinctive Art Nouveau architecture and cultural significance.
  • D. Hotel City
    Hotel City is a social-network simulation game developed by Playfish in which players design, build, and manage their own virtual hotel.
  • E. The Hotel
    The Hotel is a conceptual art project by French artist Sophie Calle in which she worked as a chambermaid to secretly observe and document hotel guests, blending photography, text, and voyeuristic narrative.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd05960008190baecb8e4c9f2461f completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cbe40d088190838819eac97c61e4 completed April 5, 2026, 8:53 p.m.
Created at: March 30, 2026, 9:01 p.m.