Triple

T15674405
Position Surface form Disambiguated ID Type / Status
Subject Brother Geraghty E377400 entity
Predicate interactsWith P3970 FINISHED
Object Oliver Bronstein E377398 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: Oliver Bronstein | Statement: [Brother Geraghty, interactsWith, Oliver Bronstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oliver Bronstein
Context triple: [Brother Geraghty, interactsWith, Oliver Bronstein]
  • A. Oliver Bronstein chosen
    Oliver Bronstein is a young boy who forms an unlikely, transformative friendship with his misanthropic neighbor in the comedy-drama film "St. Vincent."
  • B. Ollie Goldstein
    Ollie Goldstein is a songwriter best known for co-writing the pop track "Red Hot Kinda Love."
  • C. Andrew Braunsberg
    Andrew Braunsberg is a film producer best known for his work on the acclaimed 1979 satirical comedy-drama "Being There."
  • D. Oliver Coopersmith
    Oliver Coopersmith is a British actor best known for his prominent role in the television drama series "Tin Star."
  • E. Benjamin Kubelsky
    Benjamin Kubelsky, better known as Jack Benny, was a hugely influential American comedian, vaudevillian, radio and television star renowned for his impeccable timing, stingy persona, and enduring impact on 20th-century entertainment.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2c996c8190a9ebe0e92608feaa completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6edd85148190b6d5c3981204dd77 completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:16 a.m.