Triple

T19536600
Position Surface form Disambiguated ID Type / Status
Subject Birgitte Eva van Deurs E488782 entity
Predicate familyName P18 FINISHED
Object van Deurs
van Deurs is a Danish surname most notably borne by Birgitte Eva van Deurs, a figure associated with Denmark.
 E1382239 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: van Deurs | Statement: [Birgitte Eva van Deurs, familyName, van Deurs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: van Deurs
Context triple: [Birgitte Eva van Deurs, familyName, van Deurs]
  • A. van Heutsz
    Van Heutsz is a Dutch surname most prominently associated with Johannes Benedictus van Heutsz, a colonial military leader and Governor-General of the Dutch East Indies.
  • B. van den Bogaerde
    van den Bogaerde is the original Dutch family name of the British actor and writer Dirk Bogarde.
  • C. Van der Madeweg
    Van der Madeweg is a metro station in Amsterdam that serves as a stop on the city's rapid transit network.
  • D. van Amsberg
    Van Amsberg is the German-origin noble family name associated with the Dutch royal family, including members such as Prince Constantijn of the Netherlands.
  • E. van Wijnbergen
    Van Wijnbergen is a Dutch surname associated with individuals such as Everdine Huberta van Wijnbergen.
  • 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: van Deurs
Triple: [Birgitte Eva van Deurs, familyName, van Deurs]
Generated description
van Deurs is a Danish surname most notably borne by Birgitte Eva van Deurs, a figure associated with Denmark.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: van Deurs
Target entity description: van Deurs is a Danish surname most notably borne by Birgitte Eva van Deurs, a figure associated with Denmark.
  • A. van Heutsz
    Van Heutsz is a Dutch surname most prominently associated with Johannes Benedictus van Heutsz, a colonial military leader and Governor-General of the Dutch East Indies.
  • B. van den Bogaerde
    van den Bogaerde is the original Dutch family name of the British actor and writer Dirk Bogarde.
  • C. Van der Madeweg
    Van der Madeweg is a metro station in Amsterdam that serves as a stop on the city's rapid transit network.
  • D. van Amsberg
    Van Amsberg is the German-origin noble family name associated with the Dutch royal family, including members such as Prince Constantijn of the Netherlands.
  • E. van Wijnbergen
    Van Wijnbergen is a Dutch surname associated with individuals such as Everdine Huberta van Wijnbergen.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6386f0fac819081bbc29172c8965e completed April 20, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a074e814c2c81909c9203461b8378b6 completed May 15, 2026, 4:49 p.m.
NEDg Description generation batch_6a074ffa3da48190badea6039822ddd6 completed May 15, 2026, 4:55 p.m.
NED2 Entity disambiguation (via description) batch_6a0750cfe42481909bf83cc488bcbae8 completed May 15, 2026, 4:58 p.m.
Created at: April 10, 2026, 1:41 p.m.