Triple

T5148740
Position Surface form Disambiguated ID Type / Status
Subject The Babadook E116138 entity
Predicate basedOnWorkAuthor P2806 FINISHED
Object Jennifer Kent E498687 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: Jennifer Kent | Statement: [The Babadook, basedOnWorkAuthor, Jennifer Kent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jennifer Kent
Context triple: [The Babadook, basedOnWorkAuthor, Jennifer Kent]
  • A. Jennifer Kent chosen
    Jennifer Kent is an Australian filmmaker and former actress best known for writing and directing the critically acclaimed horror film "The Babadook."
  • B. Julie Kent
    Julie Kent is a renowned American ballerina celebrated for her long and distinguished career as a principal dancer and later artistic director in the world of classical ballet.
  • C. Cate Shortland
    Cate Shortland is an Australian film and television director known for character-driven dramas and for directing the Marvel superhero film "Black Widow."
  • D. Niki Caro
    Niki Caro is a New Zealand filmmaker best known for directing character-driven dramas such as "Whale Rider" and "North Country," as well as Disney's live-action "Mulan."
  • E. Karyn Kusama
    Karyn Kusama is an American film and television director known for works like "Girlfight," "Jennifer's Body," and "The Invitation," as well as her contributions to prestige TV.
  • 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_69bd4446c0e08190a7c29dc74976bf03 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd78b17028819080568715df8c13eb completed March 20, 2026, 4:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf06a74d4c8190a353007c564ba2f6 completed March 21, 2026, 8:59 p.m.
Created at: March 20, 2026, 1:43 p.m.