Triple

T7411990
Position Surface form Disambiguated ID Type / Status
Subject Hannah Simpson Grant E171026 entity
Predicate father P120 FINISHED
Object John Simpson
John Simpson was the father of Hannah Simpson Grant, making him the maternal grandfather of U.S. President Ulysses S. Grant.
 E662049 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: John Simpson | Statement: [Hannah Simpson Grant, father, John Simpson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Simpson
Context triple: [Hannah Simpson Grant, father, John Simpson]
  • A. John Simpson
    John Simpson is a prominent British journalist and long-serving foreign correspondent for the BBC.
  • B. Michael Foale
    Michael Foale is a British-American astrophysicist and former NASA astronaut renowned for his long-duration missions on the Space Shuttle and Mir, and for being one of the most experienced spacefarers in history.
  • C. Lyndon Sims
    Lyndon Sims is an individual notable primarily for bearing the given name "Lyndon."
  • D. Don Simpson
    Don Simpson was a prominent Hollywood film producer known for co-producing blockbuster action films such as "Top Gun," "Beverly Hills Cop," and "Bad Boys."
  • E. John Simpson (historical)
    John Simpson is a British lexicographer best known for serving as chief editor of the Oxford English Dictionary during a major phase of its modern revision and digitization.
  • 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: John Simpson
Triple: [Hannah Simpson Grant, father, John Simpson]
Generated description
John Simpson was the father of Hannah Simpson Grant, making him the maternal grandfather of U.S. President Ulysses S. Grant.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Simpson
Target entity description: John Simpson was the father of Hannah Simpson Grant, making him the maternal grandfather of U.S. President Ulysses S. Grant.
  • A. John Simpson
    John Simpson is a prominent British journalist and long-serving foreign correspondent for the BBC.
  • B. Michael Foale
    Michael Foale is a British-American astrophysicist and former NASA astronaut renowned for his long-duration missions on the Space Shuttle and Mir, and for being one of the most experienced spacefarers in history.
  • C. Lyndon Sims
    Lyndon Sims is an individual notable primarily for bearing the given name "Lyndon."
  • D. Don Simpson
    Don Simpson was a prominent Hollywood film producer known for co-producing blockbuster action films such as "Top Gun," "Beverly Hills Cop," and "Bad Boys."
  • E. John Simpson (historical)
    John Simpson is a British lexicographer best known for serving as chief editor of the Oxford English Dictionary during a major phase of its modern revision and digitization.
  • 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_69c68a618bdc81908d8018edadecd1a4 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2a027148190bdb6a7940389e377 completed March 27, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8112960d48190a9947146e62daa13 completed March 28, 2026, 5:34 p.m.
NEDg Description generation batch_69c811f1fe3c8190a591186b19044b5f completed March 28, 2026, 5:37 p.m.
NED2 Entity disambiguation (via description) batch_69c812c1e9d08190b0e7f052d87011b9 completed March 28, 2026, 5:41 p.m.
Created at: March 27, 2026, 3:11 p.m.