Triple
T22265797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saram Entertainment |
E550345
|
entity |
| Predicate | hasNotableClient |
P7186
|
FINISHED |
| Object | Moon So-ri |
—
|
NE NERFINISHED |
How this triple was built (2 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: Moon So-ri | Statement: [Saram Entertainment, hasNotableClient, Moon So-ri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moon So-ri Context triple: [Saram Entertainment, hasNotableClient, Moon So-ri]
-
A.
Moon So-ri
chosen
Moon So-ri is a critically acclaimed South Korean actress and director known for her powerful performances in films such as "Oasis" and "A Good Lawyer's Wife."
-
B.
Soo-an
Soo-an is the young daughter of the protagonist in the South Korean zombie film "Train to Busan," whose emotional journey and moral clarity anchor the story.
-
C.
Ju-Hee
Ju-Hee is the child of Ji-Yoon Kim, likely a member of a Korean family.
-
D.
Moon Sae-kyoung
Moon Sae-kyoung is a South Korean film editor best known for her work on acclaimed films such as Bong Joon-ho’s thriller "Mother" (2009).
-
E.
Soyeon
Soyeon is a Korean-born interpreter and the wife of former German Chancellor Gerhard Schröder.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e43d8208190aff4f9cf7f2c2a8a |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141bb850881908f5e9c37afb52ca8 |
completed | April 28, 2026, 11:24 p.m. |
Created at: April 16, 2026, 8:39 p.m.