Triple

T16799613
Position Surface form Disambiguated ID Type / Status
Subject Patrick Fabian E408320 entity
Predicate notableWork P4 FINISHED
Object Joan of Arcadia E1016360 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: Joan of Arcadia | Statement: [Patrick Fabian, notableWork, Joan of Arcadia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan of Arcadia
Context triple: [Patrick Fabian, notableWork, Joan of Arcadia]
  • A. Joan of Arcadia chosen
    Joan of Arcadia is an early-2000s American television drama series about a teenage girl who regularly encounters God in various human forms and is given tasks that affect the lives of those around her.
  • B. Rain Joan of Arc Phoenix
    Rain Joan of Arc Phoenix is an American actress and musician, known for her work in independent films and as the sister of actors River and Joaquin Phoenix.
  • C. Jeanne
    Jeanne was a common French female given name historically borne by notable figures such as queens, saints, and writers.
  • D. Angeline
    Angeline is the given name of American actress Angie Dickinson, known for her roles in film and television from the 1950s onward.
  • E. Angeline
    Angeline is a feminine given name, often considered a variant of Angélique or Angelina, used in various cultures and languages.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2acd3548190a5f6ce7d1cf74117 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab1299ac81908e9f1eebc3424bb9 completed May 10, 2026, 3:58 p.m.
Created at: April 10, 2026, 5:22 a.m.