Triple
T22582540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Tee |
E544601
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Mirelly Taylor
Mirelly Taylor is a Mexican-American actress known for her roles in film and television, including appearances on shows like Lost.
|
E1545030
|
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: Mirelly Taylor | Statement: [Brian Tee, spouse, Mirelly Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mirelly Taylor Context triple: [Brian Tee, spouse, Mirelly Taylor]
-
A.
Raquel Cassidy
Raquel Cassidy is a British actress known for her roles in television series such as Downton Abbey and Lead Balloon.
-
B.
Vinessa Shaw
Vinessa Shaw is an American actress known for her roles in films such as "Hocus Pocus," "Eyes Wide Shut," and "The Hills Have Eyes."
-
C.
Marlena Moreau
Marlena Moreau is a character from the original Star Trek series who appears in the alternate-universe episode "Mirror, Mirror" as a romantic interest of Captain Kirk.
-
D.
Nicolette Robinson
Nicolette Robinson is an American actress and singer known for her work on television and Broadway, including starring in the musical "Waitress."
-
E.
Nina Lucas
Nina Lucas is a fictional character from the British soap opera "Coronation Street," known for her gothic style, artistic talent, and relationships within the Weatherfield community.
- 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: Mirelly Taylor Triple: [Brian Tee, spouse, Mirelly Taylor]
Generated description
Mirelly Taylor is a Mexican-American actress known for her roles in film and television, including appearances on shows like Lost.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mirelly Taylor Target entity description: Mirelly Taylor is a Mexican-American actress known for her roles in film and television, including appearances on shows like Lost.
-
A.
Raquel Cassidy
Raquel Cassidy is a British actress known for her roles in television series such as Downton Abbey and Lead Balloon.
-
B.
Vinessa Shaw
Vinessa Shaw is an American actress known for her roles in films such as "Hocus Pocus," "Eyes Wide Shut," and "The Hills Have Eyes."
-
C.
Marlena Moreau
Marlena Moreau is a character from the original Star Trek series who appears in the alternate-universe episode "Mirror, Mirror" as a romantic interest of Captain Kirk.
-
D.
Nicolette Robinson
Nicolette Robinson is an American actress and singer known for her work on television and Broadway, including starring in the musical "Waitress."
-
E.
Nina Lucas
Nina Lucas is a fictional character from the British soap opera "Coronation Street," known for her gothic style, artistic talent, and relationships within the Weatherfield community.
- 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_69e11e30d05481909df915354c89f0d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f15ff26d6481908cc058f8c4b87e75 |
completed | April 29, 2026, 1:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b3d56621c81908af9a97ac77c15ba |
completed | May 18, 2026, 4:24 p.m. |
| NEDg | Description generation | batch_6a0b42e135888190ad342384a8e6a6ad |
completed | May 18, 2026, 4:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b4373b7cc8190b9eb32d9afb6bdf7 |
completed | May 18, 2026, 4:50 p.m. |
Created at: April 16, 2026, 8:53 p.m.