Triple

T7642869
Position Surface form Disambiguated ID Type / Status
Subject Doc E173049 entity
Predicate associatedWith P37 FINISHED
Object Dopey E175534 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: Dopey | Statement: [Doc, associatedWith, Dopey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dopey
Context triple: [Doc, associatedWith, Dopey]
  • A. Dopey chosen
    Dopey is the mute, childlike, and comically clumsy dwarf from Disney’s classic animated film "Snow White and the Seven Dwarfs."
  • B. Bashful
    Bashful is one of the seven dwarfs in Disney's "Snow White and the Seven Dwarfs," characterized by his shy, blushing demeanor and gentle, soft-spoken nature.
  • C. Sneezy
    Sneezy is one of the Seven Dwarfs in Disney's "Snow White and the Seven Dwarfs," known for his frequent, powerful sneezes.
  • D. Timmy Tiptoes
    Timmy Tiptoes is a squirrel character from Beatrix Potter’s children’s stories, known for his adventures and misadventures involving hoarding and protecting nuts.
  • E. Tweedledum
    Tweedledum is a rotund, childlike twin character from Lewis Carroll’s "Through the Looking-Glass," often depicted alongside his brother Tweedledee as comical and argumentative figures.
  • 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_69c6995360188190968ee57b72a1627f completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c6faef96908190a7724b204f9d8c9e completed March 27, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c870d1008c8190898a582a82038e48 completed March 29, 2026, 12:22 a.m.
Created at: March 27, 2026, 3:58 p.m.