Triple

T5166178
Position Surface form Disambiguated ID Type / Status
Subject Bela Lugosi E116562 entity
Predicate workedWith P398 FINISHED
Object Boris Karloff E218089 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: Boris Karloff | Statement: [Bela Lugosi, workedWith, Boris Karloff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boris Karloff
Context triple: [Bela Lugosi, workedWith, Boris Karloff]
  • A. Boris Karloff chosen
    Boris Karloff was an English actor best known for his iconic portrayals in classic horror films, particularly as Frankenstein's monster in the 1931 film "Frankenstein."
  • B. Bela Lugosi
    Bela Lugosi was a Hungarian-American actor best known for his iconic portrayal of Count Dracula in early horror cinema.
  • C. Vincent Price
    Vincent Price was an American actor renowned for his distinctive voice and charismatic presence, particularly in classic horror films and gothic dramas.
  • D. Vincent E. Price
    Vincent E. Price is an American political communication scholar and academic leader who serves as the president of Duke University.
  • E. Peter Cushing
    Peter Cushing was an English actor best known for his roles in classic Hammer horror films and as Grand Moff Tarkin in Star Wars.
  • 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_69bd445edb3881909b93b34d260717fc completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd792af4648190934cf2db523f6921 completed March 20, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69beefadfd3c81909d21c1a08daeca7f completed March 21, 2026, 7:21 p.m.
Created at: March 20, 2026, 1:44 p.m.