Triple

T862127
Position Surface form Disambiguated ID Type / Status
Subject Amnesty International E18620 entity
Predicate founder P104 FINISHED
Object Peter Benenson
Peter Benenson was a British lawyer and human rights activist best known for launching the international campaign that led to the creation of Amnesty International.
 E101839 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: Peter Benenson | Statement: [Amnesty International, founder, Peter Benenson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Peter Benenson
Context triple: [Amnesty International, founder, Peter Benenson]
  • A. John Humphrey
    John Humphrey was a Canadian legal scholar and human rights advocate best known as the principal drafter of the Universal Declaration of Human Rights.
  • B. Toomas Asser
    Toomas Asser is an Estonian neurosurgeon and academic who serves as the rector of the University of Tartu.
  • C. René Cassin
    René Cassin was a French jurist, Nobel Peace Prize laureate, and key architect of modern human rights law.
  • D. Stuart H. Pappé
    Stuart H. Pappé is a film editor best known for his work on the romantic comedy-drama film "The Preacher's Wife."
  • E. Deborah E. Lipstadt
    Deborah E. Lipstadt is an American historian and scholar renowned for her work on Holocaust studies and the fight against Holocaust denial.
  • 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: Peter Benenson
Triple: [Amnesty International, founder, Peter Benenson]
Generated description
Peter Benenson was a British lawyer and human rights activist best known for launching the international campaign that led to the creation of Amnesty International.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Peter Benenson
Target entity description: Peter Benenson was a British lawyer and human rights activist best known for launching the international campaign that led to the creation of Amnesty International.
  • A. John Humphrey
    John Humphrey was a Canadian legal scholar and human rights advocate best known as the principal drafter of the Universal Declaration of Human Rights.
  • B. Toomas Asser
    Toomas Asser is an Estonian neurosurgeon and academic who serves as the rector of the University of Tartu.
  • C. René Cassin
    René Cassin was a French jurist, Nobel Peace Prize laureate, and key architect of modern human rights law.
  • D. Stuart H. Pappé
    Stuart H. Pappé is a film editor best known for his work on the romantic comedy-drama film "The Preacher's Wife."
  • E. Deborah E. Lipstadt
    Deborah E. Lipstadt is an American historian and scholar renowned for her work on Holocaust studies and the fight against Holocaust denial.
  • 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_69a4938ce8688190a24bdfef82ba7d21 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac6631408190a19b83126fa86100 completed March 1, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3c5c15c8190a91eb3746007ebf5 completed March 4, 2026, 3:15 a.m.
NEDg Description generation batch_69a7a613db0881908c14569257c53bb0 completed March 4, 2026, 3:25 a.m.
NED2 Entity disambiguation (via description) batch_69a7a66cc1108190a072cc7d9be2756c completed March 4, 2026, 3:26 a.m.
Created at: March 1, 2026, 7:39 p.m.