Triple

T18464032
Position Surface form Disambiguated ID Type / Status
Subject Witchblade E451110 entity
Predicate creator P184 FINISHED
Object Marc Silvestri 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: Marc Silvestri | Statement: [Witchblade, creator, Marc Silvestri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc Silvestri
Context triple: [Witchblade, creator, Marc Silvestri]
  • A. Marc Silvestri chosen
    Marc Silvestri is an American comic book artist and publisher best known for his influential work at Marvel on titles like Uncanny X-Men and for co-founding Image Comics and creating Top Cow Productions.
  • B. Adam Garone
    Adam Garone is an Australian entrepreneur and philanthropist best known as the co-founder and former CEO of the global men's health charity movement Movember.
  • C. Michael Sardo
    Michael Sardo is a television writer and producer best known for creating the USA Network legal dramedy series "Fairly Legal."
  • D. Tom D'Andrea
    Tom D'Andrea was an American character actor known for his supporting roles in mid-20th-century films and television.
  • E. Michael Wilford
    Michael Wilford was a British architect known for his postmodern designs and for continuing the work of James Stirling on prominent cultural and public buildings.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52a8190508190a74b1d3482364905 completed April 19, 2026, 7:18 p.m.
Created at: April 10, 2026, 11:33 a.m.