Triple

T6660711
Position Surface form Disambiguated ID Type / Status
Subject Mr. Skeffington E151467 entity
Predicate starring P1507 FINISHED
Object Walter Abel E229584 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: Walter Abel | Statement: [Mr. Skeffington, starring, Walter Abel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walter Abel
Context triple: [Mr. Skeffington, starring, Walter Abel]
  • A. Walter Abel chosen
    Walter Abel was an American stage, film, and television character actor active from the silent era through the mid-20th century.
  • B. Curt Jürgens
    Curt Jürgens was a prominent German-Austrian actor known for his commanding screen presence in European cinema and Hollywood films during the mid-20th century.
  • C. Walter Herz
    Walter Herz was a graphic artist best known for designing the official poster for the 1948 Summer Olympics in London.
  • D. Ivan Goff
    Ivan Goff was an Australian-born screenwriter best known for his work in Hollywood film and television, including co-writing influential crime dramas and creating popular TV series.
  • E. Walter Bartel
    Walter Bartel was a German communist resistance fighter and politician who opposed the Nazi regime and later became a prominent figure in East Germany.
  • 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_69c687f5fac48190a09e4838d9c6b45d completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0737cb08190ad455b48fd30eec8 completed March 27, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c700755874819083cd0facebd7aa3d completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:02 p.m.