Triple

T6121923
Position Surface form Disambiguated ID Type / Status
Subject Judd Hirsch E136504 entity
Predicate familyName P18 FINISHED
Object Hirsch E508802 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: Hirsch | Statement: [Judd Hirsch, familyName, Hirsch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hirsch
Context triple: [Judd Hirsch, familyName, Hirsch]
  • A. Hirsch chosen
    Hirsch is a surname of German and Ashkenazi Jewish origin, meaning "deer," borne by various notable individuals across fields such as acting, science, and politics.
  • B. Hirschhorn
    Hirschhorn is a German-language surname borne by various notable individuals, including contemporary Swiss artist Thomas Hirschhorn.
  • C. Hirzel
    Hirzel is a small Swiss village in the canton of Zurich, known as the birthplace of "Heidi" author Johanna Spyri.
  • D. Hirt
    Hirt is a surname most notably associated with American trumpeter and bandleader Al Hirt.
  • E. Ochs
    Ochs is a surname most prominently associated with the Ochs-Sulzberger family, the longtime publishers and owners of The New York Times.
  • 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_69c0089f851c81909e5e189a617dcff6 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05bf16ad48190958cc46510e02bd3 completed March 22, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135a5c428819090066ad785296736 completed March 23, 2026, 12:44 p.m.
Created at: March 22, 2026, 4:14 p.m.