Triple
T8449831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Flying Bird |
E199772
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Sonja Sohn
Sonja Sohn is an American actress and filmmaker best known for her role as Detective Kima Greggs on the acclaimed television series "The Wire."
|
E735056
|
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: Sonja Sohn | Statement: [High Flying Bird, castMember, Sonja Sohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonja Sohn Context triple: [High Flying Bird, castMember, Sonja Sohn]
-
A.
Linda Park
Linda Park is a Korean-American actress best known for playing communications officer Hoshi Sato on the television series Star Trek: Enterprise.
-
B.
Sandra Miju Oh
Sandra Miju Oh is a Canadian-American actress best known for her acclaimed television roles in series such as "Grey's Anatomy" and "Killing Eve."
-
C.
Julie Oh
Julie Oh is a film producer known for her work on projects such as the musical drama "Tick, Tick... Boom!" (2021).
-
D.
Willa Kim
Willa Kim was an acclaimed American costume designer known for her vibrant, innovative work on Broadway, ballet, and opera, earning multiple Tony Awards over her career.
-
E.
Kyung Wha Chung
Kyung Wha Chung is a renowned South Korean violinist celebrated for her virtuosic technique and international solo career.
- 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: Sonja Sohn Triple: [High Flying Bird, castMember, Sonja Sohn]
Generated description
Sonja Sohn is an American actress and filmmaker best known for her role as Detective Kima Greggs on the acclaimed television series "The Wire."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sonja Sohn Target entity description: Sonja Sohn is an American actress and filmmaker best known for her role as Detective Kima Greggs on the acclaimed television series "The Wire."
-
A.
Linda Park
Linda Park is a Korean-American actress best known for playing communications officer Hoshi Sato on the television series Star Trek: Enterprise.
-
B.
Sandra Miju Oh
Sandra Miju Oh is a Canadian-American actress best known for her acclaimed television roles in series such as "Grey's Anatomy" and "Killing Eve."
-
C.
Julie Oh
Julie Oh is a film producer known for her work on projects such as the musical drama "Tick, Tick... Boom!" (2021).
-
D.
Willa Kim
Willa Kim was an acclaimed American costume designer known for her vibrant, innovative work on Broadway, ballet, and opera, earning multiple Tony Awards over her career.
-
E.
Kyung Wha Chung
Kyung Wha Chung is a renowned South Korean violinist celebrated for her virtuosic technique and international solo career.
- 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_69ca83170f9081909cd98f55614c6476 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe44707b88190b3d8b30c45ef4496 |
completed | March 31, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1dc85e48819083340d022d0dba9b |
completed | April 2, 2026, 7:42 a.m. |
| NEDg | Description generation | batch_69ce1f88d404819096c6024c0e61d1ea |
completed | April 2, 2026, 7:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce209338b48190ba8375200a5529bd |
completed | April 2, 2026, 7:53 a.m. |
Created at: March 30, 2026, 6:09 p.m.