Triple

T22116373
Position Surface form Disambiguated ID Type / Status
Subject Bram Fischer E546554 entity
Predicate nickname P55 FINISHED
Object Bram
Bram is the commonly used nickname of Bram Fischer, the South African lawyer and anti-apartheid activist who defended Nelson Mandela and was later imprisoned for his own resistance activities.
 E1519389 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: Bram | Statement: [Bram Fischer, nickname, Bram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bram
Context triple: [Bram Fischer, nickname, Bram]
  • A. Bramble
    Bramble is a modern classic gin-based cocktail typically made with lemon juice, sugar syrup, and blackberry liqueur, served over crushed ice.
  • B. Bramble
    Bramble is a surname most notably associated with American theatre director, author, and producer Mark Bramble.
  • C. Braman
    Braman is a small town located in northern Oklahoma in the United States.
  • D. Bromfman
    Bromfman is a surname most notably associated with Brazilian composer and music producer Pedro Bromfman, known for his work on film and television scores.
  • E. Brom
    Brom is a wise and mysterious former Dragon Rider who mentors Eragon in magic, swordsmanship, and the history of the Riders in the Inheritance Cycle series.
  • 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: Bram
Triple: [Bram Fischer, nickname, Bram]
Generated description
Bram is the commonly used nickname of Bram Fischer, the South African lawyer and anti-apartheid activist who defended Nelson Mandela and was later imprisoned for his own resistance activities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bram
Target entity description: Bram is the commonly used nickname of Bram Fischer, the South African lawyer and anti-apartheid activist who defended Nelson Mandela and was later imprisoned for his own resistance activities.
  • A. Bramble
    Bramble is a modern classic gin-based cocktail typically made with lemon juice, sugar syrup, and blackberry liqueur, served over crushed ice.
  • B. Bramble
    Bramble is a surname most notably associated with American theatre director, author, and producer Mark Bramble.
  • C. Braman
    Braman is a small town located in northern Oklahoma in the United States.
  • D. Bromfman
    Bromfman is a surname most notably associated with Brazilian composer and music producer Pedro Bromfman, known for his work on film and television scores.
  • E. Brom
    Brom is a wise and mysterious former Dragon Rider who mentors Eragon in magic, swordsmanship, and the history of the Riders in the Inheritance Cycle series.
  • 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1294dc1148190b95ff00f475a6713 completed April 28, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a8f1b4a5c8190bce19db01cd4a02f completed May 18, 2026, 4:01 a.m.
NEDg Description generation batch_6a0a913f7b3c819086c0f12562685eea completed May 18, 2026, 4:10 a.m.
NED2 Entity disambiguation (via description) batch_6a0a91d837bc8190b47ca7924f543f67 completed May 18, 2026, 4:13 a.m.
Created at: April 16, 2026, 8:31 p.m.