Triple

T9759414
Position Surface form Disambiguated ID Type / Status
Subject Lili E236631 entity
Predicate starring P1507 FINISHED
Object Kurt Kasznar E300540 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: Kurt Kasznar | Statement: [Lili, starring, Kurt Kasznar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurt Kasznar
Context triple: [Lili, starring, Kurt Kasznar]
  • A. Kurt Kasznar chosen
    Kurt Kasznar was an Austrian-American character actor known for his prolific work in mid-20th-century film, television, and theater, often portraying urbane or authoritative supporting roles.
  • B. Martin Jurow
    Martin Jurow was an American film producer best known for his work on classic mid-20th-century Hollywood movies, including the iconic Audrey Hepburn film "Breakfast at Tiffany's."
  • C. Ralph Koltai
    Ralph Koltai was a prominent British theatre designer renowned for his innovative, sculptural stage sets that transformed post-war European theatre aesthetics.
  • D. Carl Kellner
    Carl Kellner was an Austrian industrialist and esotericist best known as the principal originator of the occult initiatory organization Ordo Templi Orientis.
  • E. Walter Slezak
    Walter Slezak was an Austrian-born character actor known for his versatile roles in Hollywood films and on Broadway, often portraying charming villains or comic foils.
  • 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_69ca84d64f6c8190a4ed4e9f5936eda5 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda049995c81908569ec61805642b2 completed April 1, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d281a8e9b08190bcafaf409f83a152 completed April 5, 2026, 3:37 p.m.
Created at: March 30, 2026, 8:24 p.m.