Triple

T23216592
Position Surface form Disambiguated ID Type / Status
Subject Martinus Nijhoff E580761 entity
Predicate notableWork P4 FINISHED
Object Vormen
Vormen is a poetry collection by Dutch modernist poet Martinus Nijhoff, known for its innovative use of form and language.
 E1573175 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: Vormen | Statement: [Martinus Nijhoff, notableWork, Vormen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vormen
Context triple: [Martinus Nijhoff, notableWork, Vormen]
  • A. Formas
    Formas is a Swedish government research council that funds research in the areas of environment, agricultural sciences, and spatial planning.
  • B. Vormsi
    Vormsi is a sparsely populated Estonian island in the Baltic Sea known for its coastal landscapes, former Swedish-speaking community, and tranquil rural character.
  • C. SHAPE
    SHAPE is the central military command headquarters of NATO responsible for planning and executing the alliance’s collective defense operations in Europe.
  • D. Shape
    Shape is a health and fitness magazine and digital brand focused on exercise, nutrition, and wellness content, owned by Dotdash Meredith.
  • E. Contrasts of Forms
    Contrasts of Forms is a series of artworks exploring visual and structural oppositions in shape, composition, and design.
  • 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: Vormen
Triple: [Martinus Nijhoff, notableWork, Vormen]
Generated description
Vormen is a poetry collection by Dutch modernist poet Martinus Nijhoff, known for its innovative use of form and language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vormen
Target entity description: Vormen is a poetry collection by Dutch modernist poet Martinus Nijhoff, known for its innovative use of form and language.
  • A. Formas
    Formas is a Swedish government research council that funds research in the areas of environment, agricultural sciences, and spatial planning.
  • B. Vormsi
    Vormsi is a sparsely populated Estonian island in the Baltic Sea known for its coastal landscapes, former Swedish-speaking community, and tranquil rural character.
  • C. SHAPE
    SHAPE is the central military command headquarters of NATO responsible for planning and executing the alliance’s collective defense operations in Europe.
  • D. Shape
    Shape is a health and fitness magazine and digital brand focused on exercise, nutrition, and wellness content, owned by Dotdash Meredith.
  • E. Contrasts of Forms
    Contrasts of Forms is a series of artworks exploring visual and structural oppositions in shape, composition, and design.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f19165949c81908e4d66a8a2b0a25a completed April 29, 2026, 5:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c30ca89508190847874ab3bc1e01f completed May 19, 2026, 9:43 a.m.
NEDg Description generation batch_6a0c31f385a881908283a8b079c4128a completed May 19, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_6a0c32ece3148190a22881d69c42e948 completed May 19, 2026, 9:52 a.m.
Created at: April 17, 2026, 4:08 p.m.