Triple
T8081368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bryan Donovan |
E188622
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object |
Connor Donovan
Connor Donovan is an individual known primarily in relation to his brother, Bryan Donovan.
|
E713437
|
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: Connor Donovan | Statement: [Bryan Donovan, sibling, Connor Donovan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Connor Donovan Context triple: [Bryan Donovan, sibling, Connor Donovan]
-
A.
Connor Donovan
Connor Donovan is one of the children of American basketball coach Billy Donovan, known for his long NCAA and NBA coaching career.
-
B.
Chris Dugan
Chris Dugan is an American recording engineer and producer best known for his work with punk rock bands, including Green Day.
-
C.
Martin Donovan
Martin Donovan is an American screenwriter, director, and actor known for his work on darkly comedic and genre-blending films such as "Death Becomes Her."
-
D.
Kevin O’Donnell Jr.
Kevin O’Donnell Jr. was an American science fiction author and long-serving SFWA volunteer known for his significant contributions to the science fiction writing community.
-
E.
Conor Donovan
Conor Donovan is a fictional character from the television drama series "Ray Donovan," known as Ray's troubled teenage son.
- 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: Connor Donovan Triple: [Bryan Donovan, sibling, Connor Donovan]
Generated description
Connor Donovan is an individual known primarily in relation to his brother, Bryan Donovan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Connor Donovan Target entity description: Connor Donovan is an individual known primarily in relation to his brother, Bryan Donovan.
-
A.
Connor Donovan
Connor Donovan is one of the children of American basketball coach Billy Donovan, known for his long NCAA and NBA coaching career.
-
B.
Chris Dugan
Chris Dugan is an American recording engineer and producer best known for his work with punk rock bands, including Green Day.
-
C.
Martin Donovan
Martin Donovan is an American screenwriter, director, and actor known for his work on darkly comedic and genre-blending films such as "Death Becomes Her."
-
D.
Kevin O’Donnell Jr.
Kevin O’Donnell Jr. was an American science fiction author and long-serving SFWA volunteer known for his significant contributions to the science fiction writing community.
-
E.
Conor Donovan
Conor Donovan is a fictional character from the television drama series "Ray Donovan," known as Ray's troubled teenage son.
- 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_69ca82b662e88190b9323daab8c28a21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb40a699388190a5b8e26524ae43e5 |
completed | March 31, 2026, 3:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc93eddef48190b5f499a5b52428c8 |
completed | April 1, 2026, 3:41 a.m. |
| NEDg | Description generation | batch_69cc9557c6148190a759021b6add0a61 |
completed | April 1, 2026, 3:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc96a8bb688190a352de1798b380f1 |
completed | April 1, 2026, 3:53 a.m. |
Created at: March 30, 2026, 5:28 p.m.