Triple

T20348526
Position Surface form Disambiguated ID Type / Status
Subject Margaret March E495943 entity
Predicate spouse P13 FINISHED
Object John Brooke 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: John Brooke | Statement: [Margaret March, spouse, John Brooke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Brooke
Context triple: [Margaret March, spouse, John Brooke]
  • A. John Brooke chosen
    John Brooke is a fictional character from Louisa May Alcott's classic novel "Little Women," known as the earnest tutor who becomes Meg March's husband.
  • B. John Brooke
    John Brooke is the father of Demi Brooke.
  • C. John Brooke
    John Brooke is a notable member of the Brooke family, recognized for his prominence within this historically significant lineage.
  • D. John R. Brooke
    John R. Brooke was a United States Army general who served as the first American military governor of Cuba following the Spanish–American War.
  • E. Philip Holbrook
    Philip Holbrook is an individual notable enough to be recognized as a prominent bearer of the surname Holbrook.
  • 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_69e0b4a3320881909495ae8bc30bc2dc completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6783af5dc8190a40c3b9816cd1aef completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:24 a.m.