Triple

T5108076
Position Surface form Disambiguated ID Type / Status
Subject Thom de Graaf E115146 entity
Predicate familyName P18 FINISHED
Object de Graaf E411609 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: de Graaf | Statement: [Thom de Graaf, familyName, de Graaf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: de Graaf
Context triple: [Thom de Graaf, familyName, de Graaf]
  • A. de Graaf chosen
    De Graaf is a Dutch surname most notably associated with figures such as Reinier de Graaf, a 17th-century physician and anatomist known for his pioneering work on the reproductive system.
  • B. Ovaro
    Ovaro is a small municipality in the Carnia region of Friuli-Venezia Giulia in northeastern Italy, known as a gateway village to the famous Monte Zoncolan climb in the Alps.
  • C. Egrisi
    Egrisi was a medieval Georgian kingdom that emerged as a successor to ancient Colchis in the western Caucasus region.
  • D. Grenitote
    Grenitote is a small settlement on the island of North Uist in Scotland’s Outer Hebrides.
  • E. Neilia
    Neilia was an American educator best known as the first wife of Joe Biden, who tragically died in a car accident in 1972 along with their infant daughter.
  • 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_69bd4440b3348190be1251fd8b7951f1 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75aa6b088190b02cdb66ec4a11f0 completed March 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba9ec0fc819085dcd1d27f46f377 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:41 p.m.