Triple

T18965503
Position Surface form Disambiguated ID Type / Status
Subject Louis of Holland E464026 entity
Predicate title P38 FINISHED
Object Count of Saint-Leu — 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: Count of Saint-Leu | Statement: [Louis of Holland, title, Count of Saint-Leu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Count of Saint-Leu
Context triple: [Louis of Holland, title, Count of Saint-Leu]
  • A. Count of Saint-Leu chosen
    The Count of Saint-Leu was a noble title held by Louis Bonaparte, former King of Holland and younger brother of Napoleon Bonaparte.
  • B. Count of Blois
    The Count of Blois was a medieval French noble title associated with the powerful lords who ruled the strategically important county of Blois in central France.
  • C. Count of Arles
    Count of Arles was a medieval noble title associated with the rulership of the important Provençal city and region of Arles in what is now southern France.
  • D. Count of Arlon
    Count of Arlon was a medieval noble title associated with the region around Arlon in present-day Belgium, historically linked to the House of Limburg.
  • E. Rebecq
    Rebecq is a municipality in the Belgian province of Walloon Brabant, known for its rural character and historic watermills.
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5d663948190b496fbd2e69c7f43 completed April 20, 2026, 7:29 a.m.
Created at: April 10, 2026, noon