Triple

T12616509
Position Surface form Disambiguated ID Type / Status
Subject Milan Hejduk E301268 entity
Predicate familyName P18 FINISHED
Object Hejduk E643318 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: Hejduk | Statement: [Milan Hejduk, familyName, Hejduk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hejduk
Context triple: [Milan Hejduk, familyName, Hejduk]
  • A. Hejduk chosen
    Hejduk is a surname most notably associated with American soccer player Frankie Hejduk, a former U.S. international and Major League Soccer defender.
  • B. Haukio
    Haukio is a Finnish surname most notably borne by Jenni Haukio, a poet and the spouse of Finland’s president.
  • C. Hein
    Hein is a Dutch surname most notably borne by Piet Hein, a renowned 17th-century naval officer and folk hero of the Dutch Republic.
  • D. Heideck
    Heideck was a notable Philhellene, remembered for his support of the Greek cause during the Greek War of Independence.
  • E. Zułów
    Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
  • 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_69d7bdeaf49c8190b13800111fa77ea3 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d960c63ea48190ae1aae9280a023a6 completed April 10, 2026, 8:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ed2e12c819097cfd2a40116f491 completed May 2, 2026, 8:30 p.m.
Created at: April 9, 2026, 5:12 p.m.