Triple

T786447
Position Surface form Disambiguated ID Type / Status
Subject Eastern Norway E16813 entity
Predicate contains P35 FINISHED
Object Halden E9275 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: Halden | Statement: [Eastern Norway, contains, Halden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Halden
Context triple: [Eastern Norway, contains, Halden]
  • A. Halden chosen
    Halden is a historic border town and municipality in southeastern Norway, known for the Fredriksten fortress and its location near the Swedish border.
  • B. Gaustad
    Gaustad is a district in Oslo, Norway, known for hosting major academic and research institutions, including parts of the University of Oslo campus.
  • C. Werl Prison
    Werl Prison is a correctional facility in Werl, Germany, historically used by the Allies after World War II to incarcerate high-ranking Nazi war criminals.
  • D. Landsberg Prison
    Landsberg Prison is a Bavarian detention facility best known as the place where Adolf Hitler was incarcerated in 1924 and wrote much of "Mein Kampf."
  • E. Tøyen
    Tøyen is a neighborhood in Oslo, Norway, known for its cultural institutions, parks, and educational facilities.
  • 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_69a4936cb7448190914f5fe4b8d81607 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a77fcc6881908a025bb21e44ad56 completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69a6733e47148190bad0ac71cf45dd85 completed March 3, 2026, 5:35 a.m.
Created at: March 1, 2026, 7:38 p.m.