Triple
T21490670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foundation (TV series) |
E530226
|
entity |
| Predicate | star |
P23405
|
FINISHED |
| Object |
Sandra Yi Sencindiver
Sandra Yi Sencindiver is a Danish-Korean actress known for her work in international television and film, including a prominent role in the science fiction series "Foundation."
|
E1488159
|
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: Sandra Yi Sencindiver | Statement: [Foundation (TV series), star, Sandra Yi Sencindiver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandra Yi Sencindiver Context triple: [Foundation (TV series), star, Sandra Yi Sencindiver]
-
A.
Sandra Chung
Sandra Chung is an American linguist known for her influential work on syntax, Austronesian languages, and the interface between grammar and semantics.
-
B.
Sandra Ma
Sandra Ma is a Chinese actress known for her acclaimed performances in contemporary Chinese film and television dramas.
-
C.
Sandra Cho
Sandra Cho is the wife of Canadian actor Kevin Durand.
-
D.
Sandra Dawn Conklin
Sandra Dawn Conklin is best known as the first wife of American journalist and author Hunter S. Thompson, with whom she shared much of his early life and career.
-
E.
Emily Yokas
Emily Yokas is the daughter of NYPD officer Faith Yokas on the television drama series "Third Watch."
- 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: Sandra Yi Sencindiver Triple: [Foundation (TV series), star, Sandra Yi Sencindiver]
Generated description
Sandra Yi Sencindiver is a Danish-Korean actress known for her work in international television and film, including a prominent role in the science fiction series "Foundation."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sandra Yi Sencindiver Target entity description: Sandra Yi Sencindiver is a Danish-Korean actress known for her work in international television and film, including a prominent role in the science fiction series "Foundation."
-
A.
Sandra Chung
Sandra Chung is an American linguist known for her influential work on syntax, Austronesian languages, and the interface between grammar and semantics.
-
B.
Sandra Ma
Sandra Ma is a Chinese actress known for her acclaimed performances in contemporary Chinese film and television dramas.
-
C.
Sandra Cho
Sandra Cho is the wife of Canadian actor Kevin Durand.
-
D.
Sandra Dawn Conklin
Sandra Dawn Conklin is best known as the first wife of American journalist and author Hunter S. Thompson, with whom she shared much of his early life and career.
-
E.
Emily Yokas
Emily Yokas is the daughter of NYPD officer Faith Yokas on the television drama series "Third Watch."
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea3aee648190ba845f0c7d8110dd |
completed | April 23, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e137a64481908bf7bb6c06d7f5cc |
completed | May 17, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_6a09e27085cc8190bee06441fec7f474 |
completed | May 17, 2026, 3:44 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09e2fce69c81909d038daa7334d4a7 |
completed | May 17, 2026, 3:47 p.m. |
Created at: April 16, 2026, 6:22 p.m.