Triple

T21528484
Position Surface form Disambiguated ID Type / Status
Subject Marilyn Burns E531160 entity
Predicate workedWith P398 FINISHED
Object Gunnar Hansen NE NERFINISHED

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: Gunnar Hansen | Statement: [Marilyn Burns, workedWith, Gunnar Hansen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gunnar Hansen
Context triple: [Marilyn Burns, workedWith, Gunnar Hansen]
  • A. Gunnar Hansen chosen
    Gunnar Hansen was an Icelandic-American actor best known for originating the role of Leatherface in the 1974 horror classic "The Texas Chain Saw Massacre."
  • B. Willy Hansen
    Willy Hansen was a Danish track cyclist best known for winning multiple medals, including Olympic bronze, in the early 20th century.
  • C. Al Hansen
    Al Hansen was an American Fluxus artist and performance pioneer known for his experimental "Happenings" and collage works that challenged traditional boundaries between art and everyday life.
  • D. Armin Hansen
    Armin Hansen was an American painter known for his dynamic marine scenes and contributions to early 20th-century California art.
  • E. Gunnar Björnstrand
    Gunnar Björnstrand was a prominent Swedish stage and film actor best known for his frequent collaborations with director Ingmar Bergman.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee8852e68c8190a5341c9f75081382 completed April 26, 2026, 9:49 p.m.
Created at: April 16, 2026, 6:26 p.m.