Triple

T12236339
Position Surface form Disambiguated ID Type / Status
Subject America E291601 entity
Predicate crewMember P2094 FINISHED
Object Ronald Evans
Ronald Evans was a NASA astronaut and command module pilot best known for his role on the Apollo 17 lunar mission, during which he conducted one of the deepest spacewalks in history.
 E979247 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: Ronald Evans | Statement: [America, crewMember, Ronald Evans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ronald Evans
Context triple: [America, crewMember, Ronald Evans]
  • A. Ronald Lawrence
    Ronald Lawrence is an author known for his work on the book "Hypnotize."
  • B. Ronald Lawrence
    Ronald Lawrence is a music producer best known for his work on the Notorious B.I.G.’s hit single "Hypnotize."
  • C. Ronald Ferguson
    Ronald Ferguson was a British polo manager and former officer best known as the father of Sarah, Duchess of York.
  • D. Ronald Brooks
    Ronald Brooks is a songwriter best known for his work on the hit track "I Get Around."
  • E. Ronald Sanders
    Ronald Sanders is a Canadian film editor best known for his long-time collaboration with director David Cronenberg on numerous acclaimed films.
  • 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: Ronald Evans
Triple: [America, crewMember, Ronald Evans]
Generated description
Ronald Evans was a NASA astronaut and command module pilot best known for his role on the Apollo 17 lunar mission, during which he conducted one of the deepest spacewalks in history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ronald Evans
Target entity description: Ronald Evans was a NASA astronaut and command module pilot best known for his role on the Apollo 17 lunar mission, during which he conducted one of the deepest spacewalks in history.
  • A. Ronald Lawrence
    Ronald Lawrence is an author known for his work on the book "Hypnotize."
  • B. Ronald Lawrence
    Ronald Lawrence is a music producer best known for his work on the Notorious B.I.G.’s hit single "Hypnotize."
  • C. Ronald Ferguson
    Ronald Ferguson was a British polo manager and former officer best known as the father of Sarah, Duchess of York.
  • D. Ronald Brooks
    Ronald Brooks is a songwriter best known for his work on the hit track "I Get Around."
  • E. Ronald Sanders
    Ronald Sanders is a Canadian film editor best known for his long-time collaboration with director David Cronenberg on numerous acclaimed films.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cb2892c81909a97b3ad6ec2c21b completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62a9057408190a25f44d773b2b178 completed May 2, 2026, 4:47 p.m.
NEDg Description generation batch_69f62ef1cc4481909bc9fc768a9ef1f2 completed May 2, 2026, 5:05 p.m.
NED2 Entity disambiguation (via description) batch_69f62f808b1481908f529decdbfc5be6 completed May 2, 2026, 5:08 p.m.
Created at: April 8, 2026, 9:51 p.m.