Triple

T20807639
Position Surface form Disambiguated ID Type / Status
Subject Mordaunt Shairp E512203 entity
Predicate wrote P2831 FINISHED
Object The Green Bay 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: The Green Bay Tree | Statement: [Mordaunt Shairp, wrote, The Green Bay Tree]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Green Bay Tree
Context triple: [Mordaunt Shairp, wrote, The Green Bay Tree]
  • A. The Green Bay Tree chosen
    The Green Bay Tree is a 1933 British drama film in which Jill Esmond starred, adapted from Mordaunt Shairp’s controversial stage play about wealth, control, and emotional dependency.
  • B. McKinley Tree
    The McKinley Tree is a notable giant sequoia in California’s Giant Forest, recognized as one of the largest and most impressive trees in the world.
  • C. Lincoln Tree
    Lincoln Tree is a massive giant sequoia located in the Giant Forest of Sequoia National Park in California.
  • D. Franklin Tree
    Franklin Tree is a notable giant sequoia located in the Giant Forest of California’s Sequoia National Park.
  • E. Sycamore
    Sycamore is a small city in northern Illinois known for its historic downtown and annual Sycamore Pumpkin Festival.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d0a2a081908fb0e3d890e87aaf completed April 21, 2026, 12:20 a.m.
Created at: April 16, 2026, 12:40 p.m.