Triple
T20253732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Lee |
E498626
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mark 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: Mark Lee | Statement: [Mark Lee, name, Mark Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Lee Context triple: [Mark Lee, name, Mark Lee]
-
A.
Mark Lee
Mark Lee is an Australian actor best known for his leading role in the acclaimed World War I film "Gallipoli."
-
B.
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.
-
C.
Mark Lee
Mark Lee is a Singaporean comedian, actor, and television host known for his work in local films and variety shows.
-
D.
Marc Lee
Marc Lee is a U.S. Navy SEAL and close comrade of Chris Kyle who is depicted as a key supporting character in the film "American Sniper."
-
E.
Jack Lee
Jack Lee was a British film director best known for his work on mid-20th-century dramas and war films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e673aa42348190852ae8313f4494ca |
completed | April 20, 2026, 6:42 p.m. |
Created at: April 11, 2026, 11:41 p.m.