Triple

T7657796
Position Surface form Disambiguated ID Type / Status
Subject Helsingborg E173429 entity
Predicate hasLandmark P105 FINISHED
Object Rådhuset E310305 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: Rådhuset | Statement: [Helsingborg, hasLandmark, Rådhuset]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rådhuset
Context triple: [Helsingborg, hasLandmark, Rådhuset]
  • A. Rådhuset chosen
    Rådhuset is a Stockholm metro station on Kungsholmen, known for its cavern-like, exposed bedrock design and striking red interior.
  • B. Medborgarhuset
    Medborgarhuset is a prominent public building and cultural center in Stockholm known for its library, swimming hall, and community facilities.
  • C. Odense City Hall
    Odense City Hall is a historic municipal building in the Danish city of Odense, known for its distinctive red-brick architecture and central role in the city’s civic life.
  • D. Hillerød Town Hall
    Hillerød Town Hall is the main municipal building and administrative center of the town of Hillerød in Denmark.
  • E. Christiansborg Palace
    Christiansborg Palace is a historic government complex in central Copenhagen that houses the Danish Parliament, the Supreme Court, and the Prime Minister’s Office.
  • 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_69c69955517c819085bc715b96d304d2 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7019161548190855a5b1e9f5d7e99 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89b0d345081909a1d4475fa3876f5 completed March 29, 2026, 3:22 a.m.
Created at: March 27, 2026, 3:59 p.m.