Triple

T1204454
Position Surface form Disambiguated ID Type / Status
Subject Gary Merrill E25855 entity
Predicate residence P75 FINISHED
Object Maine, United States E29256 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: Maine, United States | Statement: [Gary Merrill, residence, Maine, United States]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maine, United States
Context triple: [Gary Merrill, residence, Maine, United States]
  • A. Maine chosen
    Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
  • B. Maine
    Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
  • C. Peru, Maine
    Peru, Maine is a small rural town in Oxford County known for its scenic western Maine landscape and close-knit community.
  • D. Strong, Maine
    Strong, Maine is a small rural town in western Maine known historically for its lumber and toothpick manufacturing industries.
  • E. Maine, Minnesota, United States
    Maine is a small unincorporated community in Minnesota, United States, known primarily as the birthplace of former U.S. Supreme Court Justice William O. Douglas.
  • 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_69a4942b30f08190a91c60573e16b5ef completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bdc0f8d08190b340012a9eb26275 completed March 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae95c9bbfc81909a02cdca9c859d01 completed March 9, 2026, 9:41 a.m.
Created at: March 1, 2026, 7:46 p.m.