Triple
T9735448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Cove |
E236045
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Kirk Krack
Kirk Krack is a renowned professional freediving instructor and safety expert known for his work in underwater training and film production.
|
E822020
|
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: Kirk Krack | Statement: [The Cove, starring, Kirk Krack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kirk Krack Context triple: [The Cove, starring, Kirk Krack]
-
A.
Kirk Stievely
Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
-
B.
Brian Krause
Brian Krause is an American actor best known for playing the whitelighter Leo Wyatt on the television series "Charmed."
-
C.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
D.
Kirk Schulz
Kirk Schulz is an American academic leader and engineer who serves as the president of Washington State University.
-
E.
Steve Kragthorpe
Steve Kragthorpe is an American football coach best known for revitalizing the University of Tulsa’s football program in the early 2000s and later serving as head coach at the University of Louisville.
- 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: Kirk Krack Triple: [The Cove, starring, Kirk Krack]
Generated description
Kirk Krack is a renowned professional freediving instructor and safety expert known for his work in underwater training and film production.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kirk Krack Target entity description: Kirk Krack is a renowned professional freediving instructor and safety expert known for his work in underwater training and film production.
-
A.
Kirk Stievely
Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
-
B.
Brian Krause
Brian Krause is an American actor best known for playing the whitelighter Leo Wyatt on the television series "Charmed."
-
C.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
D.
Kirk Schulz
Kirk Schulz is an American academic leader and engineer who serves as the president of Washington State University.
-
E.
Steve Kragthorpe
Steve Kragthorpe is an American football coach best known for revitalizing the University of Tulsa’s football program in the early 2000s and later serving as head coach at the University of Louisville.
- 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_69ca84d313e88190983ee6ffd0ef60d2 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9eee70d48190af5a833d7b33aaa5 |
completed | April 1, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1c4083b208190b0e23c4dcbea0532 |
completed | April 5, 2026, 2:08 a.m. |
| NEDg | Description generation | batch_69d1c4fc4cc88190b020f672b9f9ba27 |
completed | April 5, 2026, 2:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1c5a1cfb08190b6c16e5309dbf2b8 |
completed | April 5, 2026, 2:14 a.m. |
Created at: March 30, 2026, 8:22 p.m.