Triple
T6975597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost Dog: The Way of the Samurai |
E161708
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
John Tormey
John Tormey is an American character actor best known for his supporting role in Jim Jarmusch’s crime film "Ghost Dog: The Way of the Samurai."
|
E645243
|
NE FINISHED |
How this triple was built (4 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: John Tormey | Statement: [Ghost Dog: The Way of the Samurai, starring, John Tormey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Tormey Context triple: [Ghost Dog: The Way of the Samurai, starring, John Tormey]
-
A.
John Doherty
John Doherty is known as the husband of American actress Michael Learned, famed for her role as Olivia Walton on the television series "The Waltons."
-
B.
Tom Doherty
Tom Doherty is an American publisher best known as the founder of the science fiction and fantasy imprint Tor Books.
-
C.
Michael Costigan
Michael Costigan is a film and television producer known for his work on various high-profile projects, including serving as an executive producer on the miniseries "A Teacher."
-
D.
Stephen McDermott
Stephen McDermott is an Irish Gaelic footballer known for playing at inter-county level for Donegal.
-
E.
Don Carmody
Don Carmody is a prolific Canadian film producer known for his work on numerous commercially successful and cult-favorite films across genres.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: John Tormey Triple: [Ghost Dog: The Way of the Samurai, starring, John Tormey]
Generated description
John Tormey is an American character actor best known for his supporting role in Jim Jarmusch’s crime film "Ghost Dog: The Way of the Samurai."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Tormey Target entity description: John Tormey is an American character actor best known for his supporting role in Jim Jarmusch’s crime film "Ghost Dog: The Way of the Samurai."
-
A.
John Doherty
John Doherty is known as the husband of American actress Michael Learned, famed for her role as Olivia Walton on the television series "The Waltons."
-
B.
Tom Doherty
Tom Doherty is an American publisher best known as the founder of the science fiction and fantasy imprint Tor Books.
-
C.
Michael Costigan
Michael Costigan is a film and television producer known for his work on various high-profile projects, including serving as an executive producer on the miniseries "A Teacher."
-
D.
Stephen McDermott
Stephen McDermott is an Irish Gaelic footballer known for playing at inter-county level for Donegal.
-
E.
Don Carmody
Don Carmody is a prolific Canadian film producer known for his work on numerous commercially successful and cult-favorite films across genres.
- F. None of above. chosen
Provenance (5 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_69c68854a0d88190bc0bf82263f1afce |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db3d3ab08190b107f3229c357dd2 |
completed | March 27, 2026, 7:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ad70f09881909f1a03f295486942 |
completed | March 28, 2026, 10:29 a.m. |
| NEDg | Description generation | batch_69c7ade26e24819085f431a576d29712 |
completed | March 28, 2026, 10:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7ae9f8f648190adc5cdf08bc01d93 |
completed | March 28, 2026, 10:34 a.m. |
Created at: March 27, 2026, 2:31 p.m.