Triple
T2222157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jon Favreau |
E48163
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Joya Tillem
Joya Tillem is an American physician best known as the wife of actor and filmmaker Jon Favreau.
|
E246289
|
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: Joya Tillem | Statement: [Jon Favreau, spouse, Joya Tillem]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joya Tillem Context triple: [Jon Favreau, spouse, Joya Tillem]
-
A.
Juanita Vanoy
Juanita Vanoy is a former model and Chicago-based real estate professional best known as the ex-wife of basketball legend Michael Jordan.
-
B.
Louise Fazenda
Louise Fazenda was a prominent American silent film comedian and character actress known for her work in early Hollywood comedies.
-
C.
Mariana Keil
Mariana Keil is known primarily as a daughter of the Portuguese composer and painter Alfredo Keil, who wrote the music for Portugal’s national anthem.
-
D.
Kleggie Hermsen
Kleggie Hermsen was a professional basketball player best known for his time in the early years of the Basketball Association of America/NBA, including a stint with the Chicago Stags.
-
E.
Joan Xavier
Joan Xavier is a fictional character associated with the Doctor X universe, likely serving as a key figure in its narrative.
- 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: Joya Tillem Triple: [Jon Favreau, spouse, Joya Tillem]
Generated description
Joya Tillem is an American physician best known as the wife of actor and filmmaker Jon Favreau.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joya Tillem Target entity description: Joya Tillem is an American physician best known as the wife of actor and filmmaker Jon Favreau.
-
A.
Juanita Vanoy
Juanita Vanoy is a former model and Chicago-based real estate professional best known as the ex-wife of basketball legend Michael Jordan.
-
B.
Louise Fazenda
Louise Fazenda was a prominent American silent film comedian and character actress known for her work in early Hollywood comedies.
-
C.
Mariana Keil
Mariana Keil is known primarily as a daughter of the Portuguese composer and painter Alfredo Keil, who wrote the music for Portugal’s national anthem.
-
D.
Kleggie Hermsen
Kleggie Hermsen was a professional basketball player best known for his time in the early years of the Basketball Association of America/NBA, including a stint with the Chicago Stags.
-
E.
Joan Xavier
Joan Xavier is a fictional character associated with the Doctor X universe, likely serving as a key figure in its narrative.
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc03bfdd48190bfb96ec3e41c22dc |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae65605fa481908ac5b9d837600626 |
completed | March 9, 2026, 6:14 a.m. |
| NEDg | Description generation | batch_69ae669aa29c81909770cd69d27c274c |
completed | March 9, 2026, 6:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae66fb7f1c8190b2bc306f06c423f1 |
completed | March 9, 2026, 6:21 a.m. |
Created at: March 4, 2026, 7:47 p.m.