Triple
T22396312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee family |
E553639
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Mason 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: Mason Lee | Statement: [Lee family, hasMember, Mason Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mason Lee Context triple: [Lee family, hasMember, Mason Lee]
-
A.
Mason Lee
chosen
Mason Lee is a Taiwanese-American actor known for roles in films such as "The Hangover Part II" and for being the son of acclaimed director Ang Lee.
-
B.
Jack Soo
Jack Soo was a Japanese-American actor and comedian best known for his role as Detective Nick Yemana on the television sitcom "Barney Miller."
-
C.
Jackson Lee
Jackson Lee is the son of American producer and author Tonya Lewis Lee and acclaimed filmmaker Spike Lee.
-
D.
Kenton Lee
Kenton Lee is a natural language processing researcher best known for leading the development of ELMo contextual word embeddings at Allen Institute for AI.
-
E.
Kenton Lee
Kenton Lee is a natural language processing researcher known for his work at Google, including co-authoring the influential BERT language model.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1585e84b081908c95ed3e0d987ed8 |
completed | April 29, 2026, 1:01 a.m. |
Created at: April 16, 2026, 8:45 p.m.