Triple
T20245444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Cho |
E498412
|
entity |
| Predicate | characterPortrayed |
P1507
|
FINISHED |
| Object | Harold Lee |
E294663
|
NE FINISHED |
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: Harold Lee | Statement: [John Cho, characterPortrayed, Harold Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harold Lee Context triple: [John Cho, characterPortrayed, Harold Lee]
-
A.
Harold Lee
chosen
Harold Lee is a fictional Korean American character best known as one of the two main protagonists in the stoner comedy film series "Harold & Kumar."
-
B.
Harold Warren
Harold Warren is an alias used by Harold Finch, the reclusive billionaire tech genius from the television series "Person of Interest."
-
C.
W. Howard Lee
W. Howard Lee was an American Texas oilman best known for being married to film star Hedy Lamarr and later to actress Gene Tierney.
-
D.
Don L. Lee
Don L. Lee, better known as Haki R. Madhubuti, is an influential African American poet, essayist, and educator associated with the Black Arts Movement.
-
E.
Harold Eugene Clark
Harold Eugene Clark, better known as Gene Clark, was an American singer-songwriter and founding member of the influential folk-rock band The Byrds.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e673a26c8481908f408fb6426aece9 |
completed | April 20, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a085a1759d081909909d30925d03d72 |
completed | May 16, 2026, 11:50 a.m. |
Created at: April 11, 2026, 11:40 p.m.