Triple

T20397131
Position Surface form Disambiguated ID Type / Status
Subject Bela Lugosi E500235 entity
Predicate spouse P13 FINISHED
Object Lillian Arch 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: Lillian Arch | Statement: [Bela Lugosi, spouse, Lillian Arch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lillian Arch
Context triple: [Bela Lugosi, spouse, Lillian Arch]
  • A. Lillian Arch chosen
    Lillian Arch was the wife of iconic horror film actor Bela Lugosi, known primarily for her marriage to the legendary Dracula star.
  • B. Cassidy Arch
    Cassidy Arch is a striking natural sandstone arch and popular hiking destination located within Utah’s Capitol Reef National Park.
  • C. Tilton Arch
    Tilton Arch is a historic memorial arch in Tilton, New Hampshire, built in the late 19th century as a prominent local monument.
  • D. Leatrice Gilbert Fountain
    Leatrice Gilbert Fountain is an American author and film historian best known for her work documenting the careers of her parents, silent film star Leatrice Joy and actor John Gilbert.
  • E. Jane Lane
    Jane Lane is a fictional, sardonic high school student and aspiring artist from the animated television series "Daria."
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798b6640819085d5b12dc35633fe completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:28 a.m.