Triple

T2334770
Position Surface form Disambiguated ID Type / Status
Subject Paul Troost E44284 entity
Predicate familyName P18 FINISHED
Object Troost
Troost is a German surname most notably associated with Paul Troost, an influential early 20th-century architect.
 E256962 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: Troost | Statement: [Paul Troost, familyName, Troost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Troost
Context triple: [Paul Troost, familyName, Troost]
  • A. Trauen
    Trauen is a village in Lower Saxony, Germany, known for hosting a research facility of the German Aerospace Center (DLR).
  • B. Holthees
    Holthees is a small village in the Dutch province of North Brabant, known for its rural character and historic church.
  • C. Trostan
    Trostan is a mountain in Northern Ireland and the highest peak in County Antrim.
  • D. Vallentuna
    Vallentuna is a locality in Stockholm County, Sweden, known as a suburban community within the Stockholm metropolitan area.
  • E. Trêveszaal
    Trêveszaal is a historic meeting room in The Hague’s Binnenhof complex, traditionally used for Dutch government council meetings and important political deliberations.
  • 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: Troost
Triple: [Paul Troost, familyName, Troost]
Generated description
Troost is a German surname most notably associated with Paul Troost, an influential early 20th-century architect.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Troost
Target entity description: Troost is a German surname most notably associated with Paul Troost, an influential early 20th-century architect.
  • A. Trauen
    Trauen is a village in Lower Saxony, Germany, known for hosting a research facility of the German Aerospace Center (DLR).
  • B. Holthees
    Holthees is a small village in the Dutch province of North Brabant, known for its rural character and historic church.
  • C. Trostan
    Trostan is a mountain in Northern Ireland and the highest peak in County Antrim.
  • D. Vallentuna
    Vallentuna is a locality in Stockholm County, Sweden, known as a suburban community within the Stockholm metropolitan area.
  • E. Trêveszaal
    Trêveszaal is a historic meeting room in The Hague’s Binnenhof complex, traditionally used for Dutch government council meetings and important political deliberations.
  • 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_69a889132b488190bbb43ad4780ddd92 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc687362c8190a55b3d6cb1580d56 completed March 7, 2026, 6:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae897bf59c8190bc0ac8a4f3841832 completed March 9, 2026, 8:49 a.m.
NEDg Description generation batch_69ae8aceea58819098a98f7ad5818ac6 completed March 9, 2026, 8:54 a.m.
NED2 Entity disambiguation (via description) batch_69ae8b6c553481908b2b7b1f880b814d completed March 9, 2026, 8:57 a.m.
Created at: March 4, 2026, 7:51 p.m.