Triple

T2081038
Position Surface form Disambiguated ID Type / Status
Subject To Space and Back E45241 entity
Predicate coAuthor P398 FINISHED
Object Susan Okie
Susan Okie is an American physician and medical writer known for her work as a health and science journalist and author.
 E231440 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: Susan Okie | Statement: [To Space and Back, coAuthor, Susan Okie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Susan Okie
Context triple: [To Space and Back, coAuthor, Susan Okie]
  • A. Sonja Hogg
    Sonja Hogg is an American women's basketball coach best known for helping build Baylor University's women's program into a national contender.
  • B. Sue Johnston
    Sue Johnston is an English actress best known for her roles in television dramas such as "Brookside," "The Royle Family," and "Waking the Dead."
  • C. Ellen K. Longmire
    Ellen K. Longmire is a distinguished physicist and engineer known for her influential research and leadership in experimental fluid dynamics.
  • D. Verna Felton
    Verna Felton was an American character actress and voice performer best known for her memorable roles in classic Disney animated films.
  • E. Sherry Smith
    Sherry Smith was an early 20th-century Major League Baseball left-handed pitcher known for his strong performances in several World Series appearances.
  • 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: Susan Okie
Triple: [To Space and Back, coAuthor, Susan Okie]
Generated description
Susan Okie is an American physician and medical writer known for her work as a health and science journalist and author.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Susan Okie
Target entity description: Susan Okie is an American physician and medical writer known for her work as a health and science journalist and author.
  • A. Sonja Hogg
    Sonja Hogg is an American women's basketball coach best known for helping build Baylor University's women's program into a national contender.
  • B. Sue Johnston
    Sue Johnston is an English actress best known for her roles in television dramas such as "Brookside," "The Royle Family," and "Waking the Dead."
  • C. Ellen K. Longmire
    Ellen K. Longmire is a distinguished physicist and engineer known for her influential research and leadership in experimental fluid dynamics.
  • D. Verna Felton
    Verna Felton was an American character actress and voice performer best known for her memorable roles in classic Disney animated films.
  • E. Sherry Smith
    Sherry Smith was an early 20th-century Major League Baseball left-handed pitcher known for his strong performances in several World Series appearances.
  • 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_69a8891869c88190a02643e3bb746f59 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abba345be48190a1895f388e7749e5 completed March 7, 2026, 5:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae273ad87c8190a7b1407868692202 completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae27b2c9d08190b1950abd8d41d3b3 completed March 9, 2026, 1:51 a.m.
NED2 Entity disambiguation (via description) batch_69ae2817ce3c81908e48170760cf98ef completed March 9, 2026, 1:53 a.m.
Created at: March 4, 2026, 7:41 p.m.