Triple
T9280736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desi Lydic |
E223058
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Gannon Brousseau
Gannon Brousseau is a business executive and former actor best known as the husband of comedian and "The Daily Show" correspondent Desi Lydic.
|
E789304
|
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: Gannon Brousseau | Statement: [Desi Lydic, spouse, Gannon Brousseau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gannon Brousseau Context triple: [Desi Lydic, spouse, Gannon Brousseau]
-
A.
Christian LeBlanc
Christian LeBlanc is an American actor best known for his long-running role as Michael Baldwin on the soap opera "The Young and the Restless."
-
B.
Michele Gossett
Michele Gossett is known as the wife of American actor Robert Gossett.
-
C.
Sean Leahy
Sean Leahy is a name shared by several notable individuals, including figures in politics, sports, and the arts.
-
D.
Lee Cullen
Lee Cullen is a key protagonist in the 1996 action film "Eraser," portrayed as a whistleblower under federal protection whose testimony exposes a major arms-dealing conspiracy.
-
E.
Dominic Viens
Dominic Viens is a video game developer best known as the founder of the Quebec City–based game studio Beenox.
- 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: Gannon Brousseau Triple: [Desi Lydic, spouse, Gannon Brousseau]
Generated description
Gannon Brousseau is a business executive and former actor best known as the husband of comedian and "The Daily Show" correspondent Desi Lydic.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gannon Brousseau Target entity description: Gannon Brousseau is a business executive and former actor best known as the husband of comedian and "The Daily Show" correspondent Desi Lydic.
-
A.
Christian LeBlanc
Christian LeBlanc is an American actor best known for his long-running role as Michael Baldwin on the soap opera "The Young and the Restless."
-
B.
Michele Gossett
Michele Gossett is known as the wife of American actor Robert Gossett.
-
C.
Sean Leahy
Sean Leahy is a name shared by several notable individuals, including figures in politics, sports, and the arts.
-
D.
Lee Cullen
Lee Cullen is a key protagonist in the 1996 action film "Eraser," portrayed as a whistleblower under federal protection whose testimony exposes a major arms-dealing conspiracy.
-
E.
Dominic Viens
Dominic Viens is a video game developer best known as the founder of the Quebec City–based game studio Beenox.
- 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_69ca842123588190b3f2e1a69037d141 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd07cd9a1c8190af0521baa428ce10 |
completed | April 1, 2026, 11:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b1fef1508190a9bf1a55dd39c0ac |
completed | April 4, 2026, 6:38 a.m. |
| NEDg | Description generation | batch_69d0b2e45674819091c7e1102c8844a5 |
completed | April 4, 2026, 6:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0b36590088190a92401d5f6c4c947 |
completed | April 4, 2026, 6:44 a.m. |
Created at: March 30, 2026, 7:34 p.m.