Triple

T17008534
Position Surface form Disambiguated ID Type / Status
Subject Kirsten Munk E412636 entity
Predicate residence P75 FINISHED
Object Boller Castle E1244563 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: Boller Castle | Statement: [Kirsten Munk, residence, Boller Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boller Castle
Context triple: [Kirsten Munk, residence, Boller Castle]
  • A. Boller Castle chosen
    Boller Castle is a historic Danish manor house and former noble residence located near Horsens in Jutland.
  • B. Bouillon Castle
    Bouillon Castle is a medieval fortress in Bouillon, Belgium, best known as the stronghold of the First Crusade leader Godfrey of Bouillon and a prominent example of feudal military architecture.
  • C. Boldt Castle
    Boldt Castle is a grand early-20th-century mansion and popular tourist attraction located on Heart Island in the Thousand Islands region of the Saint Lawrence River.
  • D. Windeck Castle
    Windeck Castle is a medieval hilltop castle ruin overlooking the town of Weinheim in southwestern Germany.
  • E. Altleiningen Castle
    Altleiningen Castle is a medieval hilltop fortress in Rhineland-Palatinate, Germany, historically associated with the noble House of Leiningen and now partly used for tourism and cultural events.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d3853f548190910240a2145cc890 completed April 18, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b46e89c81908271eb22b535c558 completed May 10, 2026, 11:56 p.m.
Created at: April 10, 2026, 5:32 a.m.