Triple

T9632088
Position Surface form Disambiguated ID Type / Status
Subject BioNTech E232831 entity
Predicate hasKeyPerson P256 FINISHED
Object Ugur Sahin E812193 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: Ugur Sahin | Statement: [BioNTech, hasKeyPerson, Ugur Sahin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ugur Sahin
Context triple: [BioNTech, hasKeyPerson, Ugur Sahin]
  • A. Ugur Sahin chosen
    Ugur Sahin is a German immunologist and entrepreneur best known as the co-founder and CEO of BioNTech, the company behind one of the first mRNA-based COVID-19 vaccines.
  • B. Gökhan S. Hotamisligil
    Gökhan S. Hotamisligil is a prominent Turkish-American scientist known for his pioneering research on the molecular and genetic mechanisms linking obesity, diabetes, and metabolic disease.
  • C. Ali Fuat Cebesoy
    Ali Fuat Cebesoy was a prominent Turkish military commander and politician who played a key role in the Turkish War of Independence and the early years of the Republic of Turkey.
  • D. Oktay Caglar
    Oktay Caglar is an entrepreneur best known as one of the co-founders of the online learning platform Udemy.
  • E. Özden Toker
    Özden Toker is a Turkish public figure and philanthropist known as the daughter of Turkey’s second president and prominent statesman İsmet İnönü.
  • 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_69ca848940cc8190b97cec654cb3bb4a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b2783b48190a9929dc3e3cd2956 completed April 1, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69d189fa706c819080e8ac2411f57d93 completed April 4, 2026, 10 p.m.
Created at: March 30, 2026, 8:11 p.m.