Triple

T13919987
Position Surface form Disambiguated ID Type / Status
Subject Princess Louise of Orléans E334716 entity
Predicate deathPlace P21 FINISHED
Object Ostend, Belgium E128320 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: Ostend, Belgium | Statement: [Princess Louise of Orléans, deathPlace, Ostend, Belgium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ostend, Belgium
Context triple: [Princess Louise of Orléans, deathPlace, Ostend, Belgium]
  • A. Ostend chosen
    Ostend is a Belgian coastal city on the North Sea known for its beaches, port, and seaside tourism.
  • B. Ostend
    Ostend is a small residential and commercial settlement on Waiheke Island in New Zealand’s Hauraki Gulf.
  • C. St. Julien, Belgium
    St. Julien, Belgium is a village in the Ypres Salient of West Flanders known primarily as a major World War I battlefield site.
  • D. La Hulpe, Belgium
    La Hulpe is a small municipality in Walloon Brabant, Belgium, known for hosting the headquarters of the global financial messaging network SWIFT and for its nearby Solvay Castle and park.
  • E. Mons, Belgium
    Mons, Belgium is a historic city in the Wallonia region that serves as a key military and administrative hub, notably hosting major NATO institutions.
  • 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_69d81c5f739081908bc05b2461f54828 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2aa428ac819084e7c4b244d15f20 completed April 14, 2026, 11:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce7c4a788190a1e7619a00ab0c2e completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:16 p.m.