Triple

T4755797
Position Surface form Disambiguated ID Type / Status
Subject Roger Moore E105584 entity
Predicate spouse P13 FINISHED
Object Doorn Van Steyn
Doorn Van Steyn was a British ice skater and actress best known as the first wife of future James Bond star Roger Moore.
E676900 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: Doorn Van Steyn | Statement: [Roger Moore, spouse, Doorn Van Steyn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doorn Van Steyn
Context triple: [Roger Moore, spouse, Doorn Van Steyn]
  • A. Soestdijk
    Soestdijk is a village in the Netherlands known for its historic royal residence, Soestdijk Palace.
  • B. Nieuwenhoorn
    Nieuwenhoorn is a village in the western Netherlands that forms part of the province of South Holland.
  • C. Uithoorn
    Uithoorn is a town and municipality in the province of North Holland in the Netherlands, situated along the Amstel River.
  • D. Enkeldoorn
    Enkeldoorn is the former colonial-era name of the Zimbabwean town now known as Chivhu.
  • E. Land van Heusden
    Land van Heusden is a historic region in the northern part of the Dutch province of North Brabant, centered around the town of Heusden and known for its medieval fortifications and river landscapes.
  • 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: Doorn Van Steyn
Triple: [Roger Moore, spouse, Doorn Van Steyn]
Generated description
Doorn Van Steyn was a British ice skater and actress best known as the first wife of future James Bond star Roger Moore.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doorn Van Steyn
Target entity description: Doorn Van Steyn was a British ice skater and actress best known as the first wife of future James Bond star Roger Moore.
  • A. Soestdijk
    Soestdijk is a village in the Netherlands known for its historic royal residence, Soestdijk Palace.
  • B. Nieuwenhoorn
    Nieuwenhoorn is a village in the western Netherlands that forms part of the province of South Holland.
  • C. Uithoorn
    Uithoorn is a town and municipality in the province of North Holland in the Netherlands, situated along the Amstel River.
  • D. Enkeldoorn
    Enkeldoorn is the former colonial-era name of the Zimbabwean town now known as Chivhu.
  • E. Land van Heusden
    Land van Heusden is a historic region in the northern part of the Dutch province of North Brabant, centered around the town of Heusden and known for its medieval fortifications and river landscapes.
  • 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_69bd43f14cac819081c7c69803648211 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64e9d80c819088532921a46ea1d6 completed March 20, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8681d57c08190b72d1b010db3a065 completed March 28, 2026, 11:45 p.m.
NEDg Description generation batch_69c8690ef840819082ecaa16b5cf3f0c completed March 28, 2026, 11:49 p.m.
NED2 Entity disambiguation (via description) batch_69c86b70a51c819091590ff094e6e784 completed March 28, 2026, 11:59 p.m.
Created at: March 20, 2026, 1:20 p.m.