Triple

T23460956
Position Surface form Disambiguated ID Type / Status
Subject Henk van Woerden E568970 entity
Predicate notableWork P4 FINISHED
Object Ultramarijn
Ultramarijn is a novel by Dutch writer Henk van Woerden, known for its evocative prose and exploration of identity and displacement.
E1589739 NE FINISHED

How this triple was built (4 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: Ultramarijn | Statement: [Henk van Woerden, notableWork, Ultramarijn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ultramarijn
Context triple: [Henk van Woerden, notableWork, Ultramarijn]
  • A. Sundborn
    Sundborn is a village in central Sweden best known as the home and artistic setting of painter Carl Larsson and his family.
  • B. Schoonhovense Veer
    Schoonhovense Veer is a ferry crossing and locality on the Lek River in the Netherlands, known for connecting the town of Schoonhoven with the Krimpenerwaard region.
  • C. Flotta
    Flotta is a small island in the Orkney archipelago of Scotland, known for its oil terminal and role in North Sea petroleum operations.
  • D. Marineo
    Marineo is a small historic town in Sicily, Italy, known for its traditional architecture and scenic location near the Eleuterio River and the Ficuzza wood.
  • E. Marinha das Ondas
    Marinha das Ondas is a civil parish in the municipality of Figueira da Foz, located in the Coimbra District of central Portugal.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ultramarijn
Triple: [Henk van Woerden, notableWork, Ultramarijn]
Generated description
Ultramarijn is a novel by Dutch writer Henk van Woerden, known for its evocative prose and exploration of identity and displacement.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ultramarijn
Target entity description: Ultramarijn is a novel by Dutch writer Henk van Woerden, known for its evocative prose and exploration of identity and displacement.
  • A. Sundborn
    Sundborn is a village in central Sweden best known as the home and artistic setting of painter Carl Larsson and his family.
  • B. Schoonhovense Veer
    Schoonhovense Veer is a ferry crossing and locality on the Lek River in the Netherlands, known for connecting the town of Schoonhoven with the Krimpenerwaard region.
  • C. Flotta
    Flotta is a small island in the Orkney archipelago of Scotland, known for its oil terminal and role in North Sea petroleum operations.
  • D. Marineo
    Marineo is a small historic town in Sicily, Italy, known for its traditional architecture and scenic location near the Eleuterio River and the Ficuzza wood.
  • E. Marinha das Ondas
    Marinha das Ondas is a civil parish in the municipality of Figueira da Foz, located in the Coimbra District of central Portugal.
  • F. None of above. chosen

Provenance (5 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a69bc200819096ed2baf25cdee4f completed April 29, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c825113588190a251450dc28f737b completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6eee2f48190b4e03039c4c96abe completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca819f6dc8190852bb3c06768ac5a completed May 19, 2026, 6:12 p.m.
Created at: April 17, 2026, 5:53 p.m.