Triple
T18553247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragonfly key exchange |
E453435
|
entity |
| Predicate | hasAuthor |
P4244
|
FINISHED |
| Object |
Dan Harkins
Dan Harkins is a computer security researcher and cryptographer known for designing and contributing to widely used key exchange and authentication protocols.
|
E1397403
|
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: Dan Harkins | Statement: [Dragonfly key exchange, hasAuthor, Dan Harkins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Harkins Context triple: [Dragonfly key exchange, hasAuthor, Dan Harkins]
-
A.
Andy Haskins
Andy Haskins is a basketball executive best known for serving as the general manager of the former WNBA team Miami Sol.
-
B.
Dan Hart
Dan Hart is an aerospace executive best known as the former CEO of Virgin Orbit, where he led the company’s small-satellite launch operations.
-
C.
Larry Haines
Larry Haines was an American actor best known for his long-running role on the television soap opera "Search for Tomorrow."
-
D.
Dan Haggerty
Dan Haggerty was an American actor best known for his portrayal of the gentle mountain man in the film and television series "The Life and Times of Grizzly Adams."
-
E.
Dick Hantak
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
- 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: Dan Harkins Triple: [Dragonfly key exchange, hasAuthor, Dan Harkins]
Generated description
Dan Harkins is a computer security researcher and cryptographer known for designing and contributing to widely used key exchange and authentication protocols.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dan Harkins Target entity description: Dan Harkins is a computer security researcher and cryptographer known for designing and contributing to widely used key exchange and authentication protocols.
-
A.
Andy Haskins
Andy Haskins is a basketball executive best known for serving as the general manager of the former WNBA team Miami Sol.
-
B.
Dan Hart
Dan Hart is an aerospace executive best known as the former CEO of Virgin Orbit, where he led the company’s small-satellite launch operations.
-
C.
Larry Haines
Larry Haines was an American actor best known for his long-running role on the television soap opera "Search for Tomorrow."
-
D.
Dan Haggerty
Dan Haggerty was an American actor best known for his portrayal of the gentle mountain man in the film and television series "The Life and Times of Grizzly Adams."
-
E.
Dick Hantak
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
- 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_69d8d388b0c881908e610a1c45b52640 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e538027b94819082a4c4af66e170d7 |
completed | April 19, 2026, 8:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ccafa04c8190849980aeda8f3435 |
completed | May 16, 2026, 1:47 a.m. |
| NEDg | Description generation | batch_6a07cfbebe848190a1e7cce64ec19df9 |
completed | May 16, 2026, 2 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07d050623c8190bfd3c05193794101 |
completed | May 16, 2026, 2:02 a.m. |
Created at: April 10, 2026, 11:38 a.m.