Triple
T14071044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Dillon |
E338607
|
entity |
| Predicate | characterRole |
P268
|
FINISHED |
| Object |
Bunny
Bunny is a brutal and sadistic U.S. soldier portrayed by Kevin Dillon in the Vietnam War film "Platoon."
|
E1078102
|
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: Bunny | Statement: [Kevin Dillon, characterRole, Bunny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bunny Context triple: [Kevin Dillon, characterRole, Bunny]
-
A.
Bunny
Bunny is a supporting character in the psychological thriller film "Don't Worry Darling," portrayed as a seemingly content housewife whose role becomes more complex as the story’s unsettling reality is revealed.
-
B.
Bunny
"Bunny" is a 2005 Telugu-language romantic action film starring Allu Arjun, known for its energetic performances, catchy music, and mass appeal.
-
C.
Bunny
Bunny is a small village and civil parish in Nottinghamshire, England, known for its historic church and rural character.
-
D.
Bunny
Bunny is an Oscar-winning animated short film by Blue Sky Studios, renowned for its emotional storytelling and pioneering use of computer-generated imagery.
-
E.
Bean Bunny
Bean Bunny is a small, enthusiastic rabbit Muppet character known for his cute appearance and supporting roles in various Muppet productions.
- 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: Bunny Triple: [Kevin Dillon, characterRole, Bunny]
Generated description
Bunny is a brutal and sadistic U.S. soldier portrayed by Kevin Dillon in the Vietnam War film "Platoon."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bunny Target entity description: Bunny is a brutal and sadistic U.S. soldier portrayed by Kevin Dillon in the Vietnam War film "Platoon."
-
A.
Bunny
Bunny is a supporting character in the psychological thriller film "Don't Worry Darling," portrayed as a seemingly content housewife whose role becomes more complex as the story’s unsettling reality is revealed.
-
B.
Bunny
Bunny is an Oscar-winning animated short film by Blue Sky Studios, renowned for its emotional storytelling and pioneering use of computer-generated imagery.
-
C.
Bunny
"Bunny" is a 2005 Telugu-language romantic action film starring Allu Arjun, known for its energetic performances, catchy music, and mass appeal.
-
D.
Bunny
Bunny is a small village and civil parish in Nottinghamshire, England, known for its historic church and rural character.
-
E.
Bean Bunny
Bean Bunny is a small, enthusiastic rabbit Muppet character known for his cute appearance and supporting roles in various Muppet productions.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5aa828819098ef55a70a0decbc |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb66cfe2c8190af8354316d4f4df9 |
completed | May 7, 2026, 3:57 p.m. |
| NEDg | Description generation | batch_69fcc5c893dc81908538136e0f9170ca |
completed | May 7, 2026, 5:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fcc64ac93c8190ad40a04c74f70e18 |
completed | May 7, 2026, 5:05 p.m. |
Created at: April 9, 2026, 10:21 p.m.