Triple

T9312328
Position Surface form Disambiguated ID Type / Status
Subject libsodium E224033 entity
Predicate creator P184 FINISHED
Object Frank Denis
Frank Denis is a software engineer and security expert best known for creating the libsodium cryptographic library.
E792094 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: Frank Denis | Statement: [libsodium, creator, Frank Denis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Denis
Context triple: [libsodium, creator, Frank Denis]
  • A. Denis Paul
    Denis Paul was a scholar and editor known for his work on Ludwig Wittgenstein’s posthumously published philosophical writings.
  • B. Fred Forbat
    Fred Forbat was a Hungarian-born modernist architect and urban planner associated with the Bauhaus movement and influential European social housing projects.
  • C. Denis Barnett
    Denis Barnett was a senior Royal Air Force officer who rose to high command during and after the Second World War.
  • D. Jack Denison
    Jack Denison was an American nightclub owner and restaurateur best known as the second husband of actress and singer Dorothy Dandridge.
  • E. Eugene Roche
    Eugene Roche was an American character actor known for his prolific work in film and television, often playing affable or comedic supporting roles.
  • 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: Frank Denis
Triple: [libsodium, creator, Frank Denis]
Generated description
Frank Denis is a software engineer and security expert best known for creating the libsodium cryptographic library.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank Denis
Target entity description: Frank Denis is a software engineer and security expert best known for creating the libsodium cryptographic library.
  • A. Denis Paul
    Denis Paul was a scholar and editor known for his work on Ludwig Wittgenstein’s posthumously published philosophical writings.
  • B. Fred Forbat
    Fred Forbat was a Hungarian-born modernist architect and urban planner associated with the Bauhaus movement and influential European social housing projects.
  • C. Denis Barnett
    Denis Barnett was a senior Royal Air Force officer who rose to high command during and after the Second World War.
  • D. Jack Denison
    Jack Denison was an American nightclub owner and restaurateur best known as the second husband of actress and singer Dorothy Dandridge.
  • E. Eugene Roche
    Eugene Roche was an American character actor known for his prolific work in film and television, often playing affable or comedic supporting roles.
  • 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_69ca8425f4fc81909c1c586e9a5b7530 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd20ae96e481909a1af9ea1c91f2b2 completed April 1, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0c797640c8190be003e321faf3b86 completed April 4, 2026, 8:11 a.m.
NEDg Description generation batch_69d0cb9605608190b0c5f7149b2194a9 completed April 4, 2026, 8:28 a.m.
NED2 Entity disambiguation (via description) batch_69d0cd0028048190a94cd7e8971f8940 completed April 4, 2026, 8:34 a.m.
Created at: March 30, 2026, 7:37 p.m.