Triple

T5973470
Position Surface form Disambiguated ID Type / Status
Subject Lord High Treasurer of Sweden E132928 entity
Predicate officeHolder P537 FINISHED
Object Lars von Engeström
Lars von Engeström was a Swedish statesman and diplomat who became one of the leading political figures of his time, notably serving in top governmental roles during the early 19th century.
E559795 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: Lars von Engeström | Statement: [Lord High Treasurer of Sweden, officeHolder, Lars von Engeström]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lars von Engeström
Context triple: [Lord High Treasurer of Sweden, officeHolder, Lars von Engeström]
  • A. Andrea diSessa
    Andrea diSessa is an American educational researcher and cognitive scientist known for his work on physics education, computational literacy, and the design of learning environments.
  • B. Janus Friis
    Janus Friis is a Danish entrepreneur best known for co-founding the internet communications platform Skype.
  • C. Jens Blauert
    Jens Blauert is a German acoustician renowned for his pioneering work in spatial hearing and psychoacoustics.
  • D. Nikolaj Bjørner
    Nikolaj Bjørner is a computer scientist best known for his work on automated theorem proving and the development of the Z3 SMT solver.
  • E. Eero Haapalainen
    Eero Haapalainen was a Finnish socialist politician and military leader who served as the commander-in-chief of the Red Guards during the Finnish Civil War.
  • 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: Lars von Engeström
Triple: [Lord High Treasurer of Sweden, officeHolder, Lars von Engeström]
Generated description
Lars von Engeström was a Swedish statesman and diplomat who became one of the leading political figures of his time, notably serving in top governmental roles during the early 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lars von Engeström
Target entity description: Lars von Engeström was a Swedish statesman and diplomat who became one of the leading political figures of his time, notably serving in top governmental roles during the early 19th century.
  • A. Andrea diSessa
    Andrea diSessa is an American educational researcher and cognitive scientist known for his work on physics education, computational literacy, and the design of learning environments.
  • B. Janus Friis
    Janus Friis is a Danish entrepreneur best known for co-founding the internet communications platform Skype.
  • C. Jens Blauert
    Jens Blauert is a German acoustician renowned for his pioneering work in spatial hearing and psychoacoustics.
  • D. Nikolaj Bjørner
    Nikolaj Bjørner is a computer scientist best known for his work on automated theorem proving and the development of the Z3 SMT solver.
  • E. Eero Haapalainen
    Eero Haapalainen was a Finnish socialist politician and military leader who served as the commander-in-chief of the Red Guards during the Finnish Civil War.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a01dd4081909097342afff31f9b completed March 22, 2026, 7:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e40fa2488190b82d604d51b73090 completed March 23, 2026, 6:56 a.m.
NEDg Description generation batch_69c0f85e33d8819080d9d721421b4c5b completed March 23, 2026, 8:22 a.m.
NED2 Entity disambiguation (via description) batch_69c0fad0bdf08190bf6599d492848582 completed March 23, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:03 p.m.