Triple

T11429663
Position Surface form Disambiguated ID Type / Status
Subject John Henry Kagi E270844 entity
Predicate parent P120 FINISHED
Object Mary Kagi
Mary Kagi was the mother of abolitionist John Henry Kagi, who was a key lieutenant of John Brown during the lead-up to the American Civil War.
E924917 NE FINISHED

How this triple was built (4 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: Mary Kagi | Statement: [John Henry Kagi, parent, Mary Kagi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Kagi
Context triple: [John Henry Kagi, parent, Mary Kagi]
  • A. Kim Brown
    Kim Brown is an individual known primarily through a close personal association with Tiffy Gerhardt.
  • B. Kim Brown
    Kim Brown is the central protagonist of "The Unit," around whom the story’s events and character dynamics primarily revolve.
  • C. Kim Brown
    Kim Brown is a person known primarily as a relative of Bob Brown.
  • D. Lacey Beaty
    Lacey Beaty is an American politician who serves as the mayor of Beaverton, Oregon, and is known for being the city's first female mayor.
  • E. Bob Ferguson
    Bob Ferguson is an American lawyer and politician who serves as the Attorney General of Washington State, known for leading numerous high-profile legal challenges on consumer protection, civil rights, and federal policies.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary Kagi
Triple: [John Henry Kagi, parent, Mary Kagi]
Generated description
Mary Kagi was the mother of abolitionist John Henry Kagi, who was a key lieutenant of John Brown during the lead-up to the American Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Kagi
Target entity description: Mary Kagi was the mother of abolitionist John Henry Kagi, who was a key lieutenant of John Brown during the lead-up to the American Civil War.
  • A. Kim Brown
    Kim Brown is an individual known primarily through a close personal association with Tiffy Gerhardt.
  • B. Kim Brown
    Kim Brown is a person known primarily as a relative of Bob Brown.
  • C. Kim Brown
    Kim Brown is the central protagonist of "The Unit," around whom the story’s events and character dynamics primarily revolve.
  • D. Lacey Beaty
    Lacey Beaty is an American politician who serves as the mayor of Beaverton, Oregon, and is known for being the city's first female mayor.
  • E. Bob Ferguson
    Bob Ferguson is an American lawyer and politician who serves as the Attorney General of Washington State, known for leading numerous high-profile legal challenges on consumer protection, civil rights, and federal policies.
  • F. None of above. chosen

Provenance (5 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d806c1bfb881909720c74fe0fa837f completed April 9, 2026, 8:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8d923688190bb4d61d57768e10e completed April 20, 2026, 5:25 a.m.
NEDg Description generation batch_69e5c28e2dd481909b45a43b5825f393 completed April 20, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69e5c4722c348190a4c49edb1f6df240 completed April 20, 2026, 6:15 a.m.
Created at: April 8, 2026, 9:35 p.m.