Triple
T14691374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emily the Criminal |
E345042
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
John Patton Ford
John Patton Ford is an American filmmaker best known for writing and directing the crime thriller film "Emily the Criminal."
|
E1114321
|
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 Patton Ford | Statement: [Emily the Criminal, director, John Patton Ford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Patton Ford Context triple: [Emily the Criminal, director, John Patton Ford]
-
A.
Robert Newton Ford
Robert Newton Ford was an American outlaw best known for killing Jesse James, an act that made him infamous in the history of the Old West.
-
B.
Frank Ford
Frank Ford is a relatively obscure individual whose specific notability is unclear from the given information alone.
-
C.
James Sawyer Ford
James "Sawyer" Ford is a central character on the television series "Lost," known as a complex, sharp-tongued con man with a troubled past and evolving moral compass.
-
D.
John Gardner Ford
John Gardner Ford is the son of former U.S. President Gerald Ford and First Lady Betty Ford, known as a member of the Ford family.
-
E.
Peter Ford
Peter Ford is the son of classic Hollywood actor Glenn Ford and has worked as an actor, producer, and biographer of his father.
- 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 Patton Ford Triple: [Emily the Criminal, director, John Patton Ford]
Generated description
John Patton Ford is an American filmmaker best known for writing and directing the crime thriller film "Emily the Criminal."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Patton Ford Target entity description: John Patton Ford is an American filmmaker best known for writing and directing the crime thriller film "Emily the Criminal."
-
A.
Robert Newton Ford
Robert Newton Ford was an American outlaw best known for killing Jesse James, an act that made him infamous in the history of the Old West.
-
B.
Frank Ford
Frank Ford is a relatively obscure individual whose specific notability is unclear from the given information alone.
-
C.
James Sawyer Ford
James "Sawyer" Ford is a central character on the television series "Lost," known as a complex, sharp-tongued con man with a troubled past and evolving moral compass.
-
D.
John Gardner Ford
John Gardner Ford is the son of former U.S. President Gerald Ford and First Lady Betty Ford, known as a member of the Ford family.
-
E.
Peter Ford
Peter Ford is the son of classic Hollywood actor Glenn Ford and has worked as an actor, producer, and biographer of his father.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb585d46c81908d6964130914cec4 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde18b4bdc8190b5daf05484de7cd8 |
completed | May 8, 2026, 1:13 p.m. |
| NEDg | Description generation | batch_69fde5c65ce0819092a385e92243a3c7 |
completed | May 8, 2026, 1:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fde638f42c8190ba56f9e2f4b03090 |
completed | May 8, 2026, 1:33 p.m. |
Created at: April 10, 2026, 1:28 a.m.