Triple

T18059903
Position Surface form Disambiguated ID Type / Status
Subject SF Sergel E432142 entity
Predicate formerNameOf P65 FINISHED
Object Filmstaden Sergel NE NERFINISHED

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: Filmstaden Sergel | Statement: [SF Sergel, formerNameOf, Filmstaden Sergel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Filmstaden Sergel
Context triple: [SF Sergel, formerNameOf, Filmstaden Sergel]
  • A. Filmstaden Sergel chosen
    Filmstaden Sergel is a large, modern multiplex cinema in central Stockholm known for showing mainstream films and hosting major movie premieres.
  • B. Filmstaden Bergakungen
    Filmstaden Bergakungen is a large, modern cinema complex in Gothenburg, Sweden, known for its multiple screens and premium movie-going experience.
  • C. Opernring
    Opernring is a prominent section of Vienna’s Ringstrasse boulevard that runs past the Vienna State Opera and several other notable cultural and historic buildings.
  • D. Folkparken
    Folkparken is a prominent public park in Norrköping, Sweden, known as a central green space for recreation and community events.
  • E. Bavaria Filmstadt
    Bavaria Filmstadt is a film-themed visitor attraction and studio tour in Munich where guests can explore sets, props, and behind-the-scenes aspects of movie and television production.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c10583648190a161c58abf4853d5 completed April 19, 2026, 11:48 a.m.
Created at: April 10, 2026, 10:26 a.m.