Triple
T17904958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael K. Williams |
E447676
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Bessie |
—
|
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: Bessie | Statement: [Michael K. Williams, notableWork, Bessie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bessie Context triple: [Michael K. Williams, notableWork, Bessie]
-
A.
Bessie
Bessie is the Third Doctor’s iconic vintage yellow roadster from Doctor Who, used as his primary mode of terrestrial transport.
-
B.
Bessie
chosen
Bessie is a biographical drama film about blues singer Bessie Smith, directed by Dee Rees.
-
C.
Bessie
Bessie is a feminine given name most famously associated with legendary American blues singer Bessie Smith.
-
D.
Bessie
Bessie is a character from "The Land of Dreams," likely serving as a central figure within its imaginative, dreamlike narrative world.
-
E.
Bessie
Bessie is one of the central child protagonists in Enid Blyton’s classic fantasy series "The Magic Faraway Tree," known for her sensible and caring nature during the siblings’ adventures.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e9b643c8190a01e9ec4caa88183 |
completed | April 19, 2026, 9:21 a.m. |
Created at: April 10, 2026, 10:19 a.m.