Triple

T11436344
Position Surface form Disambiguated ID Type / Status
Subject Hans Kelsen E271019 entity
Predicate familyName P18 FINISHED
Object Kelsen E271019 NE FINISHED

How this triple was built (2 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: Kelsen | Statement: [Hans Kelsen, familyName, Kelsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelsen
Context triple: [Hans Kelsen, familyName, Kelsen]
  • A. Hans Kelsen chosen
    Hans Kelsen was an influential Austrian legal theorist best known for developing the Pure Theory of Law and shaping modern constitutional and international legal thought.
  • B. Rudolf von Jhering
    Rudolf von Jhering was a 19th-century German jurist and legal theorist known for his influential work on the social purpose of law and the development of sociological jurisprudence.
  • C. Eugen Ehrlich
    Eugen Ehrlich was an Austrian legal scholar and sociologist of law known for pioneering the concept of "living law" and influencing the development of legal realism.
  • D. Friedrich Karl von Savigny
    Friedrich Karl von Savigny was a prominent 19th-century German jurist and legal scholar, best known as a founder of the historical school of law.
  • E. Toomas Asser
    Toomas Asser is an Estonian neurosurgeon and academic who serves as the rector of the University of Tartu.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d808855a7481909314f90ad92aae68 completed April 9, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e8ed579c8190b1ddc1dce20d9617 completed April 20, 2026, 8:50 a.m.
Created at: April 8, 2026, 9:35 p.m.