Triple

T6097273
Position Surface form Disambiguated ID Type / Status
Subject Renato Dulbecco E135907 entity
Predicate doctoralAdvisor P167 FINISHED
Object Giuseppe Levi E393789 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: Giuseppe Levi | Statement: [Renato Dulbecco, doctoralAdvisor, Giuseppe Levi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Giuseppe Levi
Context triple: [Renato Dulbecco, doctoralAdvisor, Giuseppe Levi]
  • A. Giuseppe Levi chosen
    Giuseppe Levi was an Italian physician and pioneering histologist known for his influential work in cell biology and for mentoring several future Nobel laureates.
  • B. Giuseppe Adami
    Giuseppe Adami was an Italian playwright and librettist best known for his collaborations with composer Giacomo Puccini on several of his operas.
  • C. Giuseppe Boffa
    Giuseppe Boffa was an Italian communist politician, journalist, and historian known for his influential writings on Soviet and Italian political history.
  • D. Guido Carlesi
    Guido Carlesi is an Italian former professional road cyclist known for his strong stage race performances in the early 1960s.
  • E. Lamberto Zannier
    Lamberto Zannier is an Italian diplomat and former OSCE Secretary General known for his work in conflict prevention, minority rights, and European security affairs.
  • 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_69c0087cd3c48190b459848c72d84eb1 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05a987ce081908cbe22940f31ee2f completed March 22, 2026, 9:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1254365708190b8feb95dfb2b730d completed March 23, 2026, 11:34 a.m.
Created at: March 22, 2026, 4:12 p.m.