Triple

T10073516
Position Surface form Disambiguated ID Type / Status
Subject Mae Costello E213686 entity
Predicate relative P37 FINISHED
Object Maurice Costello E219591 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: Maurice Costello | Statement: [Mae Costello, relative, Maurice Costello]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maurice Costello
Context triple: [Mae Costello, relative, Maurice Costello]
  • A. Maurice Costello chosen
    Maurice Costello was an American stage and silent film actor often regarded as one of the first matinee idols in motion pictures.
  • B. Maurice McDonald
    Maurice McDonald was an American entrepreneur who, with his brother Richard, created the original fast-food restaurant concept that evolved into the global McDonald’s chain.
  • C. Johnny Loughran
    Johnny Loughran is the energetic, easygoing human who becomes Dracula’s son-in-law and a central comedic character in the Hotel Transylvania animated film series.
  • D. Arthur Dignam
    Arthur Dignam was an Australian actor known for his distinctive character roles in film, television, and theatre.
  • E. Arthur O'Connell
    Arthur O'Connell was an American character actor known for his supporting roles in mid-20th-century films and stage productions, often portraying kindly or world-weary older men.
  • 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd015ad488190aee3a2bfb58fb855 completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b649b7488190ad765d4ee6eac5d7 completed April 5, 2026, 7:21 p.m.
Created at: March 30, 2026, 8:59 p.m.