Triple

T16258115
Position Surface form Disambiguated ID Type / Status
Subject Frank De Winne E394682 entity
Predicate familyName P18 FINISHED
Object De Winne
De Winne is the surname of Frank De Winne, a Belgian Air Force officer and European Space Agency astronaut known for commanding the International Space Station.
E1202744 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: De Winne | Statement: [Frank De Winne, familyName, De Winne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: De Winne
Context triple: [Frank De Winne, familyName, De Winne]
  • A. Ockenga
    Ockenga is a surname most notably associated with Harold Ockenga, a prominent American evangelical leader and theologian.
  • B. Wallesau
    Wallesau is a village-level subdivision of the town of Roth in the Bavarian region of Germany.
  • C. De Bolle
    De Bolle is the surname of Catherine De Bolle, a prominent Belgian police official and former Executive Director of Europol.
  • D. Weener
    Weener is a small town and municipality in the Leer district of Lower Saxony in northwestern Germany, known for its historic harbor and location on the River Ems.
  • E. Wiebe
    Wiebe is a given name and surname of Frisian and Dutch origin, used in various forms across the Netherlands and surrounding regions.
  • 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: De Winne
Triple: [Frank De Winne, familyName, De Winne]
Generated description
De Winne is the surname of Frank De Winne, a Belgian Air Force officer and European Space Agency astronaut known for commanding the International Space Station.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: De Winne
Target entity description: De Winne is the surname of Frank De Winne, a Belgian Air Force officer and European Space Agency astronaut known for commanding the International Space Station.
  • A. Ockenga
    Ockenga is a surname most notably associated with Harold Ockenga, a prominent American evangelical leader and theologian.
  • B. Wallesau
    Wallesau is a village-level subdivision of the town of Roth in the Bavarian region of Germany.
  • C. De Bolle
    De Bolle is the surname of Catherine De Bolle, a prominent Belgian police official and former Executive Director of Europol.
  • D. Weener
    Weener is a small town and municipality in the Leer district of Lower Saxony in northwestern Germany, known for its historic harbor and location on the River Ems.
  • E. Wiebe
    Wiebe is a given name and surname of Frisian and Dutch origin, used in various forms across the Netherlands and surrounding regions.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c1fa208190995feaeba766b45f completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000eebcfe481909822290d3a7b361c completed May 10, 2026, 4:51 a.m.
NEDg Description generation batch_6a000f8cca5081909db58e092028e469 completed May 10, 2026, 4:54 a.m.
NED2 Entity disambiguation (via description) batch_6a001057f9088190925492033bcd4c8d completed May 10, 2026, 4:58 a.m.
Created at: April 10, 2026, 5:04 a.m.