Triple

T3079137
Position Surface form Disambiguated ID Type / Status
Subject Yu-Chi Ho E64210 entity
Predicate notableStudent P4838 FINISHED
Object Isaac Horowitz E221767 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: Isaac Horowitz | Statement: [Yu-Chi Ho, notableStudent, Isaac Horowitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isaac Horowitz
Context triple: [Yu-Chi Ho, notableStudent, Isaac Horowitz]
  • A. Isaac Horowitz chosen
    Isaac Horowitz was a prominent control theorist and engineer known for his influential contributions to feedback control system design and robust control theory.
  • B. Isaac Goldberg
    Isaac Goldberg was an American author, critic, and translator known for his works on literature, music, and Latin American culture in the early 20th century.
  • C. Isaac Abuhav
    Isaac Abuhav was a prominent 15th-century Spanish rabbi and kabbalist whose teachings and legacy are commemorated by the historic Abuhav Synagogue in Safed.
  • D. Isaac Wolfson
    Isaac Wolfson was a British businessman and philanthropist best known for building the Great Universal Stores retail empire and for his extensive charitable contributions to education and science.
  • E. Isaac Ehrlich
    Isaac Ehrlich is an economist known for his work on the economic analysis of crime, deterrence, and the death penalty.
  • 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_69ad857bb4c88190a4cf27893fcabed8 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1a86a848190a47ca127cc7e6326 completed March 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b65076d970819098246f2533b7519f completed March 15, 2026, 6:23 a.m.
Created at: March 8, 2026, 3:02 p.m.