Triple

T3810298
Position Surface form Disambiguated ID Type / Status
Subject Samuel Osgood E93115 entity
Predicate spouse P13 FINISHED
Object Mary Marston
Mary Marston was the wife of Samuel Osgood, an early American political figure and the first U.S. Postmaster General.
E390481 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 Marston | Statement: [Samuel Osgood, spouse, Mary Marston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Marston
Context triple: [Samuel Osgood, spouse, Mary Marston]
  • A. Martha Coleman
    Martha Coleman is a film producer known for her work on the British comedy-drama "Praise."
  • B. Jo Grant
    Jo Grant is a spirited and resourceful companion of the Third Doctor in the classic British science fiction series Doctor Who.
  • C. Alex Scott
    Alex Scott was an Australian actor known for his work in film and television, including a role in the controversial 1992 drama "Romper Stomper."
  • D. Jennifer Walters
    Jennifer Walters is a Marvel Comics lawyer who becomes the superhero She-Hulk after receiving a blood transfusion from her cousin Bruce Banner.
  • E. Sally Blane
    Sally Blane was an American film actress of the early 20th century who appeared in numerous silent and sound films, often in supporting roles.
  • 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 Marston
Triple: [Samuel Osgood, spouse, Mary Marston]
Generated description
Mary Marston was the wife of Samuel Osgood, an early American political figure and the first U.S. Postmaster General.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Marston
Target entity description: Mary Marston was the wife of Samuel Osgood, an early American political figure and the first U.S. Postmaster General.
  • A. Martha Coleman
    Martha Coleman is a film producer known for her work on the British comedy-drama "Praise."
  • B. Jo Grant
    Jo Grant is a spirited and resourceful companion of the Third Doctor in the classic British science fiction series Doctor Who.
  • C. Alex Scott
    Alex Scott was an Australian actor known for his work in film and television, including a role in the controversial 1992 drama "Romper Stomper."
  • D. Jennifer Walters
    Jennifer Walters is a Marvel Comics lawyer who becomes the superhero She-Hulk after receiving a blood transfusion from her cousin Bruce Banner.
  • E. Sally Blane
    Sally Blane was an American film actress of the early 20th century who appeared in numerous silent and sound films, often in supporting roles.
  • 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_69aed96a60088190ab1df8390fffc935 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aee80e178081908cff71223bbf6c43 completed March 9, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb33db9c81908b462ee80aaaad34 completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fc08d65081908953482b10fa5611 completed March 14, 2026, 6:11 a.m.
NED2 Entity disambiguation (via description) batch_69b4fc7d8cf081909c4447818b5363c5 completed March 14, 2026, 6:13 a.m.
Created at: March 9, 2026, 3:16 p.m.