Triple
T19798353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doug Besterman |
E475602
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Fosse |
—
|
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: Fosse | Statement: [Doug Besterman, notableWork, Fosse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fosse Context triple: [Doug Besterman, notableWork, Fosse]
-
A.
Fosse
chosen
Fosse is a musical revue celebrating the choreography and legacy of director-choreographer Bob Fosse, featuring signature numbers from his stage and film work.
-
B.
Fosse
Fosse is a village that forms one of the constituent localities of the municipality of Trois-Ponts in the province of Liège, Belgium.
-
C.
Fosse Dionne
Fosse Dionne is a historic, enigmatic karst spring and circular stone pool in Tonnerre, France, long associated with legends and notable for its unusually deep, turquoise waters.
-
D.
Florenz
Florenz was the first name of Florenz Ziegfeld Jr., the influential American Broadway impresario best known for creating the Ziegfeld Follies.
-
E.
Garfinkle
Garfinkle is the original surname of American actor John Garfield, a prominent film star of the 1930s and 1940s known for his intense, naturalistic performances.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c877288190b56ee7eedea710a3 |
completed | April 20, 2026, 4:26 p.m. |
Created at: April 10, 2026, 1:49 p.m.