Triple
T8364468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 U.S. Figure Skating Championships |
E197090
|
entity |
| Predicate | notableCompetitor |
P11706
|
FINISHED |
| Object |
Jason Dungjen
Jason Dungjen is an American former pair skater and coach best known for his successful partnership with Kyoko Ina in the 1990s.
|
E728023
|
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: Jason Dungjen | Statement: [1997 U.S. Figure Skating Championships, notableCompetitor, Jason Dungjen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jason Dungjen Context triple: [1997 U.S. Figure Skating Championships, notableCompetitor, Jason Dungjen]
-
A.
Ryan Hudson
Ryan Hudson is an entrepreneur best known as the co-founder of Honey, the popular online shopping and coupon-finding browser extension acquired by PayPal.
-
B.
Adrian Vandenberg
Adrian Vandenberg is a Dutch rock guitarist best known for his work with Whitesnake and his own band Vandenberg.
-
C.
Ryan Dusick
Ryan Dusick is an American musician best known as the original drummer and a founding member of the pop rock band Maroon 5.
-
D.
Jason Sehorn
Jason Sehorn is a former American football cornerback best known for his NFL career with the New York Giants in the 1990s and early 2000s.
-
E.
Ryan Amon
Ryan Amon is a film composer best known for his powerful, futuristic score for the science fiction movie "Elysium."
- 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: Jason Dungjen Triple: [1997 U.S. Figure Skating Championships, notableCompetitor, Jason Dungjen]
Generated description
Jason Dungjen is an American former pair skater and coach best known for his successful partnership with Kyoko Ina in the 1990s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jason Dungjen Target entity description: Jason Dungjen is an American former pair skater and coach best known for his successful partnership with Kyoko Ina in the 1990s.
-
A.
Ryan Hudson
Ryan Hudson is an entrepreneur best known as the co-founder of Honey, the popular online shopping and coupon-finding browser extension acquired by PayPal.
-
B.
Adrian Vandenberg
Adrian Vandenberg is a Dutch rock guitarist best known for his work with Whitesnake and his own band Vandenberg.
-
C.
Ryan Dusick
Ryan Dusick is an American musician best known as the original drummer and a founding member of the pop rock band Maroon 5.
-
D.
Jason Sehorn
Jason Sehorn is a former American football cornerback best known for his NFL career with the New York Giants in the 1990s and early 2000s.
-
E.
Ryan Amon
Ryan Amon is a film composer best known for his powerful, futuristic score for the science fiction movie "Elysium."
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb808a67f88190849152102bfeb574 |
completed | March 31, 2026, 8:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc78497cc8190a88bb5934f31e1f7 |
completed | April 2, 2026, 1:33 a.m. |
| NEDg | Description generation | batch_69cdcc88456c8190ba8613b4cbf40fbb |
completed | April 2, 2026, 1:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cdcd75714881908f0b069a94ee334f |
completed | April 2, 2026, 1:59 a.m. |
Created at: March 30, 2026, 6 p.m.