Triple

T19727490
Position Surface form Disambiguated ID Type / Status
Subject Dekker E473763 entity
Predicate hasNotableBearer P458 FINISHED
Object Sjoerd Dekker
Sjoerd Dekker is a relatively obscure individual whose primary current distinction is simply being noted as a bearer of the surname Dekker.
 E1398584 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: Sjoerd Dekker | Statement: [Dekker, hasNotableBearer, Sjoerd Dekker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sjoerd Dekker
Context triple: [Dekker, hasNotableBearer, Sjoerd Dekker]
  • A. Martin Dekker
    Martin Dekker is a fictional character appearing in the Doctor Who audio drama "The Silence."
  • B. Sander van Doorn
    Sander van Doorn is a Dutch DJ and electronic music producer known for his influential work in trance and progressive house.
  • C. Jeroen van der Boom
    Jeroen van der Boom is a Dutch singer, television presenter, and entertainer known for his successful music career and prominent roles on Dutch TV talent shows.
  • D. Sjoerd Soeters
    Sjoerd Soeters is a Dutch architect known for his postmodern, human-scaled urban designs and influential waterfront redevelopment projects in the Netherlands.
  • E. Jelle Nijdam
    Jelle Nijdam is a retired Dutch professional road cyclist known for his strong time-trialing abilities and multiple stage wins in major European races.
  • 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: Sjoerd Dekker
Triple: [Dekker, hasNotableBearer, Sjoerd Dekker]
Generated description
Sjoerd Dekker is a relatively obscure individual whose primary current distinction is simply being noted as a bearer of the surname Dekker.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sjoerd Dekker
Target entity description: Sjoerd Dekker is a relatively obscure individual whose primary current distinction is simply being noted as a bearer of the surname Dekker.
  • A. Martin Dekker
    Martin Dekker is a fictional character appearing in the Doctor Who audio drama "The Silence."
  • B. Sander van Doorn
    Sander van Doorn is a Dutch DJ and electronic music producer known for his influential work in trance and progressive house.
  • C. Jeroen van der Boom
    Jeroen van der Boom is a Dutch singer, television presenter, and entertainer known for his successful music career and prominent roles on Dutch TV talent shows.
  • D. Sjoerd Soeters
    Sjoerd Soeters is a Dutch architect known for his postmodern, human-scaled urban designs and influential waterfront redevelopment projects in the Netherlands.
  • E. Jelle Nijdam
    Jelle Nijdam is a retired Dutch professional road cyclist known for his strong time-trialing abilities and multiple stage wins in major European races.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649f95d5c8190858ba414ff3e95a8 completed April 20, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07d428853c8190b7df67f52e59ba32 completed May 16, 2026, 2:19 a.m.
NEDg Description generation batch_6a07d6a8e5c88190915b3ea03cb0460d completed May 16, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_6a07d7292fd88190b913904b1050cd4b completed May 16, 2026, 2:32 a.m.
Created at: April 10, 2026, 1:47 p.m.