Triple

T5356556
Position Surface form Disambiguated ID Type / Status
Subject Mike Hill E102705 entity
Predicate notableWork P4 FINISHED
Object Cocoon E13793 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: Cocoon | Statement: [Mike Hill, notableWork, Cocoon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cocoon
Context triple: [Mike Hill, notableWork, Cocoon]
  • A. Cocoon chosen
    Cocoon is a 1985 science fiction comedy-drama film about a group of elderly people who regain youth and vitality after encountering alien life, directed by Ron Howard.
  • B. Cocoon
    Cocoon is an acclaimed indie puzzle-adventure video game known for its innovative world-within-worlds mechanic and atmospheric, wordless storytelling.
  • C. The Cradle
    The Cradle is an 1872 Impressionist painting by Berthe Morisot depicting a tender scene of a mother watching over her sleeping child, and is considered one of her most celebrated works.
  • D. Hothouse
    Hothouse is an American television drama series from the late 1980s in which Michael Learned starred as a psychiatrist working in a psychiatric hospital.
  • E. Forest of Illusion
    Forest of Illusion is a secret-filled, maze-like forest world in Super Mario World known for its tricky level exits and hidden paths.
  • 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_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd862f0ea48190bec78690ab3bee51 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21e2b7b08190aca4c2855ff041de completed March 21, 2026, 10:55 p.m.
Created at: March 20, 2026, 2:01 p.m.