Triple

T22101862
Position Surface form Disambiguated ID Type / Status
Subject Victim E546190 entity
Predicate starring P1507 FINISHED
Object Dirk Bogarde 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: Dirk Bogarde | Statement: [Victim, starring, Dirk Bogarde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dirk Bogarde
Context triple: [Victim, starring, Dirk Bogarde]
  • A. Dirk Bogarde chosen
    Dirk Bogarde was a distinguished British actor and author known for his nuanced performances in mid-20th-century cinema and later acclaimed literary career.
  • B. David Niven
    David Niven was a distinguished English actor known for his suave, debonair screen presence and acclaimed roles in films such as "Around the World in 80 Days" and "Separate Tables."
  • C. Peter O'Toole
    Peter O'Toole was an acclaimed Irish-English actor renowned for his charismatic screen presence and multiple Academy Award–nominated performances across film, stage, and television.
  • D. Omar Sharif
    Omar Sharif was an acclaimed Egyptian actor known internationally for his roles in classic films such as "Lawrence of Arabia" and "Doctor Zhivago."
  • E. Herbert Lom
    Herbert Lom was a Czech-born British actor best known for his versatile character roles in films such as "The Pink Panther" series, "Spartacus," and numerous classic British and Hollywood productions.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129163b908190b63ace06016f4db8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.