Triple
T15624940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Last Station |
E375655
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Michael Hoffman |
E398580
|
NE FINISHED |
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: Michael Hoffman | Statement: [The Last Station, director, Michael Hoffman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Hoffman Context triple: [The Last Station, director, Michael Hoffman]
-
A.
Michael Hoffman
chosen
Michael Hoffman is a common name shared by several notable individuals, including film directors, authors, and academics.
-
B.
Gregg Hoffman
Gregg Hoffman was an American film producer best known for helping launch and shape the successful horror franchise "Saw."
-
C.
Andrew Dorff
Andrew Dorff was an American country music songwriter known for penning hits for artists such as Blake Shelton, Kenny Chesney, and Rascal Flatts.
-
D.
Timothy Busfield
Timothy Busfield is an American actor and director best known for his roles in television series such as "thirtysomething," "The West Wing," and various film and stage productions.
-
E.
Michael Culver
Michael Culver is a British actor known for his character roles in film and television, including appearances in productions such as "A Passage to India" and "The Empire Strikes Back."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9e5e248190ae54cda1fde51efb |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff678c9d8c8190be73b6e7ed558e99 |
completed | May 9, 2026, 4:57 p.m. |
Created at: April 10, 2026, 4:14 a.m.