Triple

T19526565
Position Surface form Disambiguated ID Type / Status
Subject Dorothy Tree E488533 entity
Predicate name P16 FINISHED
Object Dorothy Tree 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: Dorothy Tree | Statement: [Dorothy Tree, name, Dorothy Tree]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dorothy Tree
Context triple: [Dorothy Tree, name, Dorothy Tree]
  • A. Dorothy Tree chosen
    Dorothy Tree was an American character actress and acting teacher known for her supporting roles in numerous films from the 1930s to the 1950s and for coaching many prominent performers.
  • B. Dorothy Vallens
    Dorothy Vallens is a troubled nightclub singer at the center of the dark, surreal mystery in David Lynch's film "Blue Velvet."
  • C. Ms. Tree
    Ms. Tree is a hard-boiled crime comic series created by Max Allan Collins, featuring a tough female private investigator who navigates gritty, noir-style mysteries.
  • D. Dorothy Good
    Dorothy Good was a young child accused of witchcraft during the Salem witch trials in colonial Massachusetts.
  • E. Dorothy Spinner
    Dorothy Spinner is a DC Comics character associated with the Doom Patrol, known for her simian-like appearance and powerful ability to bring imaginary beings to life.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363aeb8c8190be2bdd73e421af96 completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.