Triple
T21480821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tammy and the Doctor |
E529983
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Harry Keller |
—
|
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: Harry Keller | Statement: [Tammy and the Doctor, director, Harry Keller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Keller Context triple: [Tammy and the Doctor, director, Harry Keller]
-
A.
Harry Keller
chosen
Harry Keller was an American film editor and director known for his work on numerous mid-20th-century Hollywood productions.
-
B.
John Gallaudet
John Gallaudet was an American character actor known for his numerous supporting roles in mid-20th-century films and television.
-
C.
Mark O’Brien
Mark O’Brien is an American local politician who has served as the mayor of Augusta, Maine.
-
D.
Mark O'Brien
Mark O'Brien is an American actor best known for his roles in television series such as City on a Hill and Halt and Catch Fire, as well as various film and independent projects.
-
E.
Mark O'Brien
Mark O'Brien is a Canadian actor, writer, and director known for his work in film and television, including writing the screenplay for the film "The Righteous."
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1b0130819088b8e96ddbb29317 |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:20 p.m.