Triple
T20178368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goosebumps (2015 film) |
E492657
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Ryan 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: Ryan Lee | Statement: [Goosebumps (2015 film), castMember, Ryan Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryan Lee Context triple: [Goosebumps (2015 film), castMember, Ryan Lee]
-
A.
Ryan Lee
chosen
Ryan Lee is an American actor best known for his role in the science-fiction film "Super 8" and appearances in various film and television projects.
-
B.
Craig Lee
Craig Lee is known as the child of prominent American politician Barbara Lee.
-
C.
Andrew Daulton Lee
Andrew Daulton Lee is a former American drug dealer and convicted Soviet spy whose espionage activities during the Cold War inspired the film "The Falcon and the Snowman."
-
D.
Greg Lee
Greg Lee is an American actor and comedian best known for hosting the 1990s children's geography game show "Where in the World Is Carmen Sandiego?"
-
E.
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.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ed07c8819091bd9ffda237a91c |
completed | April 20, 2026, 5:57 p.m. |
Created at: April 11, 2026, 11:36 p.m.