Triple

T9281330
Position Surface form Disambiguated ID Type / Status
Subject Heather Graham E223073 entity
Predicate appearedIn P795 FINISHED
Object From Hell E789919 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: From Hell | Statement: [Heather Graham, appearedIn, From Hell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: From Hell
Context triple: [Heather Graham, appearedIn, From Hell]
  • A. From Hell chosen
    From Hell is a 2001 dark mystery horror film about the Jack the Ripper murders, starring Heather Graham and Johnny Depp and based on the graphic novel by Alan Moore and Eddie Campbell.
  • B. The Black Book
    The Black Book is a postmodern novel by Turkish author Orhan Pamuk that blends mystery, philosophical reflection, and Istanbul’s labyrinthine atmosphere to explore identity and storytelling.
  • C. The Black Book
    The Black Book is a film featuring Portuguese actress Daniela Melchior in its cast.
  • D. The Charnel House
    The Charnel House is a 1945 painting by Pablo Picasso that depicts a twisted, skeletal pile of bodies as a powerful condemnation of war and human atrocity.
  • E. Vile Bodies
    Vile Bodies is a satirical novel by Evelyn Waugh that portrays the reckless, hedonistic lifestyle of England’s interwar “Bright Young Things.”
  • 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_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081c2b048190aa6930de3bf2f87f completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0c750723c8190b874aa238d01d658 completed April 4, 2026, 8:09 a.m.
Created at: March 30, 2026, 7:34 p.m.