Triple

T18259716
Position Surface form Disambiguated ID Type / Status
Subject The Ghost of Frankenstein E437315 entity
Predicate stars P1956 FINISHED
Object Bela Lugosi 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: Bela Lugosi | Statement: [The Ghost of Frankenstein, stars, Bela Lugosi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bela Lugosi
Context triple: [The Ghost of Frankenstein, stars, Bela Lugosi]
  • A. Bela Lugosi chosen
    Bela Lugosi was a Hungarian-American actor best known for his iconic portrayal of Count Dracula in early horror cinema.
  • B. Bela Lugosi Jr.
    Bela Lugosi Jr. is an American attorney and the son of legendary horror film actor Bela Lugosi, known for his legal work related to his father's legacy and likeness rights.
  • C. Boris Karloff
    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."
  • D. Chris Karloff
    Chris Karloff is an English musician and songwriter best known as a founding guitarist and key early songwriter of the rock band Kasabian.
  • E. Lillian Arch Lugosi
    Lillian Arch Lugosi was the wife of actor Brian Donlevy and is primarily known for her marriage to him.
  • 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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4fd89899c8190b8b652c4f61aa5cf completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 10:34 a.m.