Triple
T20751402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rama II |
E510727
|
entity |
| Predicate | coAuthor |
P398
|
FINISHED |
| Object | Gentry 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: Gentry Lee | Statement: [Rama II, coAuthor, Gentry Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gentry Lee Context triple: [Rama II, coAuthor, Gentry Lee]
-
A.
Gentry Lee
chosen
Gentry Lee is an American aerospace engineer and science fiction author best known for collaborating with Arthur C. Clarke on several novels, including the later books in the Rama series.
-
B.
Garret Lee
Garret Lee is an Irish music producer and mixer best known under the professional name Jacknife Lee, noted for his work with major rock and alternative bands.
-
C.
Kenton Lee
Kenton Lee is a natural language processing researcher known for his work at Google, including co-authoring the influential BERT language model.
-
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.
Eli Nunn
Eli Nunn is the child of English actress and writer Imogen Stubbs.
- 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_69e0b4c909ec8190b05987f1639513f6 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c22ad0c8819087a8db2bac8dd408 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:34 p.m.