Triple
T20083647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bluebird |
E500066
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Charles Greene |
—
|
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: Charles Greene | Statement: [Bluebird, producer, Charles Greene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Greene Context triple: [Bluebird, producer, Charles Greene]
-
A.
Charles Greene
Charles Greene is the son of Canadian actor and broadcaster Lorne Greene, best known for his role in the television series "Bonanza."
-
B.
Charles Greene
chosen
Charles Greene was an American record producer and music manager best known for his work in the 1960s and 1970s rock scene, including collaborations with bands like Iron Butterfly.
-
C.
Joseph Greene
Joseph Greene was a Canadian Liberal politician who served as a Member of Parliament and was a candidate in the 1968 Liberal Party of Canada leadership race.
-
D.
Herbert Greene
Herbert Greene was an American Broadway conductor and musical director best known for his work on classic mid-20th-century stage productions.
-
E.
Frank Greene
Frank Greene is an American jazz and studio trumpeter best known for his work as a member of the CBS Orchestra on the "Late Show with David Letterman."
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655946f48190a6b4cb13ea4e212a |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 3:41 p.m.