Triple
T19999193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bering Sea Gold |
E494272
|
entity |
| Predicate | features |
P997
|
FINISHED |
| Object |
Brad Kelly
Brad Kelly is a gold dredger and reality television personality known for appearing on the Discovery Channel series "Bering Sea Gold."
|
E1405412
|
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: Brad Kelly | Statement: [Bering Sea Gold, features, Brad Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad Kelly Context triple: [Bering Sea Gold, features, Brad Kelly]
-
A.
Craig Kelly
Craig Kelly is a British actor best known for his roles in television series such as "Queer as Folk" and "Hotel Babylon."
-
B.
Collin Wilcox
Collin Wilcox was an American actress best known for her role as Mayella Ewell in the classic film adaptation of "To Kill a Mockingbird."
-
C.
Kevin McCall
Kevin McCall is an American singer, songwriter, rapper, and producer known for his work in contemporary R&B and hip hop, including collaborations with artists like Chris Brown.
-
D.
Jake Scott
Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
-
E.
Jake Scott
Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
- 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: Brad Kelly Triple: [Bering Sea Gold, features, Brad Kelly]
Generated description
Brad Kelly is a gold dredger and reality television personality known for appearing on the Discovery Channel series "Bering Sea Gold."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brad Kelly Target entity description: Brad Kelly is a gold dredger and reality television personality known for appearing on the Discovery Channel series "Bering Sea Gold."
-
A.
Craig Kelly
Craig Kelly is a British actor best known for his roles in television series such as "Queer as Folk" and "Hotel Babylon."
-
B.
Collin Wilcox
Collin Wilcox was an American actress best known for her role as Mayella Ewell in the classic film adaptation of "To Kill a Mockingbird."
-
C.
Kevin McCall
Kevin McCall is an American singer, songwriter, rapper, and producer known for his work in contemporary R&B and hip hop, including collaborations with artists like Chris Brown.
-
D.
Jake Scott
Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
-
E.
Jake Scott
Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a09bdc819083305b08a11c6e34 |
completed | April 20, 2026, 5:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a080509d0748190a2703a2e3ddb0fc1 |
completed | May 16, 2026, 5:47 a.m. |
| NEDg | Description generation | batch_6a0806563e1c8190b702fcfc009c84d5 |
completed | May 16, 2026, 5:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0806e876c881909f0c30e5dd16ce20 |
completed | May 16, 2026, 5:55 a.m. |
Created at: April 11, 2026, 3:32 p.m.