Triple

T8395744
Position Surface form Disambiguated ID Type / Status
Subject Wonder Woman 1984 E198047 entity
Predicate cinematographyBy P1953 FINISHED
Object Matthew Jensen E289645 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: Matthew Jensen | Statement: [Wonder Woman 1984, cinematographyBy, Matthew Jensen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Jensen
Context triple: [Wonder Woman 1984, cinematographyBy, Matthew Jensen]
  • A. Matthew Jensen chosen
    Matthew Jensen is a cinematographer best known for his work on major films such as the 2017 superhero movie "Wonder Woman."
  • B. David Jensen
    David Jensen is a musician known for his work with the soft rock/R&B-influenced indie supergroup Gayngs.
  • C. John Luessenhop
    John Luessenhop is an American film director and screenwriter best known for helming genre and action films, including the horror sequel "Texas Chainsaw 3D."
  • D. Jason Sehorn
    Jason Sehorn is a former American football cornerback best known for his NFL career with the New York Giants in the 1990s and early 2000s.
  • E. Michael Christensen
    Michael Christensen is a Danish professional racing driver known for competing in international sports car and endurance racing events, including the FIA World Endurance Championship.
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb81874d6c8190bbc0ac832d8a339d completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d046efb42c8190b19c8ecd5efa8956 completed April 3, 2026, 11:02 p.m.
Created at: March 30, 2026, 6:04 p.m.