Triple

T11999376
Position Surface form Disambiguated ID Type / Status
Subject Elyse Knox E285616 entity
Predicate spouse P13 FINISHED
Object Paul Hesse
Paul Hesse was the husband of American actress and fashion designer Elyse Knox.
E958962 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: Paul Hesse | Statement: [Elyse Knox, spouse, Paul Hesse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Hesse
Context triple: [Elyse Knox, spouse, Paul Hesse]
  • A. Johannes Hesse
    Johannes Hesse was a Baltic German missionary and publisher best known as the father of the Nobel Prize–winning author Hermann Hesse.
  • B. Alberta Hesse
    Alberta Hesse was the wife of American crime novelist Jim Thompson.
  • C. Johann Heermann
    Johann Heermann was a notable early 17th-century German Lutheran hymn writer and poet whose texts were widely used in Protestant church music.
  • D. Hal Morgenstern
    Hal Morgenstern is an American epidemiologist known for his contributions to cancer epidemiology and methods in observational study design.
  • E. Hermann Hess
    Hermann Hess was a mountaineer known for making the first recorded ascent of Monte San Valentín, the highest peak in Chilean Patagonia.
  • 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: Paul Hesse
Triple: [Elyse Knox, spouse, Paul Hesse]
Generated description
Paul Hesse was the husband of American actress and fashion designer Elyse Knox.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paul Hesse
Target entity description: Paul Hesse was the husband of American actress and fashion designer Elyse Knox.
  • A. Johannes Hesse
    Johannes Hesse was a Baltic German missionary and publisher best known as the father of the Nobel Prize–winning author Hermann Hesse.
  • B. Alberta Hesse
    Alberta Hesse was the wife of American crime novelist Jim Thompson.
  • C. Johann Heermann
    Johann Heermann was a notable early 17th-century German Lutheran hymn writer and poet whose texts were widely used in Protestant church music.
  • D. Hal Morgenstern
    Hal Morgenstern is an American epidemiologist known for his contributions to cancer epidemiology and methods in observational study design.
  • E. Hermann Hess
    Hermann Hess was a mountaineer known for making the first recorded ascent of Monte San Valentín, the highest peak in Chilean Patagonia.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903c26d7881909b67a31d04882eb5 completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f472917ed08190a872d9e5663d5ed5 completed May 1, 2026, 9:29 a.m.
NEDg Description generation batch_69f47b7e4a40819085680c48eed5418a completed May 1, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_69f47df40a8c8190bd7350ba27f57214 completed May 1, 2026, 10:18 a.m.
Created at: April 8, 2026, 9:46 p.m.