Triple

T12534266
Position Surface form Disambiguated ID Type / Status
Subject Frederiksberg Campus E299647 entity
Predicate hasNeighbour P5707 FINISHED
Object Copenhagen Zoo E888239 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: Copenhagen Zoo | Statement: [Frederiksberg Campus, hasNeighbour, Copenhagen Zoo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Copenhagen Zoo
Context triple: [Frederiksberg Campus, hasNeighbour, Copenhagen Zoo]
  • A. Copenhagen Zoo chosen
    Copenhagen Zoo is one of Denmark’s oldest and most visited zoological gardens, known for its diverse animal collection and distinctive architecture, including the iconic wooden observation tower.
  • B. Odense Zoo
    Odense Zoo is a popular Danish zoological garden in the city of Odense, known for its diverse animal collections and family-friendly exhibits.
  • C. Hanover Zoo
    Hanover Zoo is a major zoological garden in Hanover, Germany, known for its themed animal habitats and immersive visitor experiences.
  • D. Zurich Zoo
    Zurich Zoo is a major zoological garden in Zurich, Switzerland, known for its diverse animal exhibits and conservation-focused, naturalistic habitats.
  • E. Prague Zoo
    Prague Zoo is a major zoological garden in Prague renowned for its extensive animal collections, conservation programs, and scenic location along the Vltava River.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546b8fd48190ae90e80785b2e2d1 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc9b9ec8190a25e2658d79836bc completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.