Triple

T22176415
Position Surface form Disambiguated ID Type / Status
Subject Astonishing X-Men E548061 entity
Predicate notableWriter P10455 FINISHED
Object Marjorie Liu 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: Marjorie Liu | Statement: [Astonishing X-Men, notableWriter, Marjorie Liu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marjorie Liu
Context triple: [Astonishing X-Men, notableWriter, Marjorie Liu]
  • A. Marjorie Liu chosen
    Marjorie Liu is an American novelist and comic book writer best known for her work on Marvel titles and for co-creating the acclaimed fantasy comic series *Monstress*.
  • B. Margaret Bennett
    Margaret Bennett is known as the wife of British drummer and composer Brian Bennett, famed for his work with the band The Shadows.
  • C. Sophie McShera
    Sophie McShera is an English actress best known for her roles as Daisy Mason in the television series "Downton Abbey" and as one of the stepsisters in Disney’s live-action "Cinderella."
  • D. Christie Golden
    Christie Golden is an American author best known for her tie-in novels set in popular franchises such as Star Wars, World of Warcraft, and Star Trek.
  • E. Molly Quinn
    Molly Quinn is an American actress best known for her role as Alexis Castle on the TV series "Castle" and for supporting film roles including an appearance in the comedy "We're the Millers."
  • 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_69e11e3d53f88190a2b690e3f25bb062 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a6c40988190ba52ea46079eb306 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.