Triple
T20388191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beef |
E498012
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Joseph Lee |
—
|
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: Joseph Lee | Statement: [Beef, stars, Joseph Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joseph Lee Context triple: [Beef, stars, Joseph Lee]
-
A.
Joseph Lee
chosen
Joseph Lee is a Korean-American actor and artist known for his roles in film and television, including a supporting role in the thriller "Searching" (2018).
-
B.
Don Lee
Don Lee was a prominent early 20th-century American broadcasting pioneer and automobile dealer whose influence in Los Angeles led to Mount Lee being named in his honor.
-
C.
Don Lee
Don Lee, also known by his Korean name Ma Dong-seok, is a South Korean-American actor renowned for his tough, charismatic roles in action and thriller films such as "Train to Busan" and various Korean crime dramas.
-
D.
Mark Lee
Mark Lee is a prominent contemporary architect known for his minimalist, context-sensitive designs and leadership of the Los Angeles–based firm Johnston Marklee.
-
E.
Mark Lee
Mark Lee is a Singaporean comedian, actor, and television host known for his work in local films and variety shows.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790d9e5881908bde7da9e5e541a0 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.