Triple
T18912173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secretary (2002 film) |
E462634
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Amy Hobby
Amy Hobby is an American film producer known for her work on independent and arthouse films, including the Oscar-nominated documentary "What Happened, Miss Simone?".
|
E1349444
|
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: Amy Hobby | Statement: [Secretary (2002 film), producer, Amy Hobby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Hobby Context triple: [Secretary (2002 film), producer, Amy Hobby]
-
A.
Beth Botsford
Beth Botsford is an American former competitive swimmer and Olympic gold medalist known for her success in backstroke events in the 1990s.
-
B.
Phyllis Housen
Phyllis Housen is a film editor known for her work on the movie "Clemency."
-
C.
Enid Hoopes
Enid Hoopes is a feminist, socially conscious law student character in the Broadway musical adaptation of "Legally Blonde."
-
D.
Kath Pettingill
Kath Pettingill is an Australian matriarch and convicted criminal best known as the leader of the notorious Pettingill crime family in Melbourne.
-
E.
Lois Robbins
Lois Robbins is an American actress known for her work in television, film, and theater, including roles on soap operas like "One Life to Live" and "All My Children."
- 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: Amy Hobby Triple: [Secretary (2002 film), producer, Amy Hobby]
Generated description
Amy Hobby is an American film producer known for her work on independent and arthouse films, including the Oscar-nominated documentary "What Happened, Miss Simone?".
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Amy Hobby Target entity description: Amy Hobby is an American film producer known for her work on independent and arthouse films, including the Oscar-nominated documentary "What Happened, Miss Simone?".
-
A.
Beth Botsford
Beth Botsford is an American former competitive swimmer and Olympic gold medalist known for her success in backstroke events in the 1990s.
-
B.
Phyllis Housen
Phyllis Housen is a film editor known for her work on the movie "Clemency."
-
C.
Enid Hoopes
Enid Hoopes is a feminist, socially conscious law student character in the Broadway musical adaptation of "Legally Blonde."
-
D.
Kath Pettingill
Kath Pettingill is an Australian matriarch and convicted criminal best known as the leader of the notorious Pettingill crime family in Melbourne.
-
E.
Lois Robbins
Lois Robbins is an American actress known for her work in television, film, and theater, including roles on soap operas like "One Life to Live" and "All My Children."
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c6238e288190b30311b5d80beafb |
completed | April 20, 2026, 6:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05910ffc8081908738b5e7ef08d52c |
completed | May 14, 2026, 9:08 a.m. |
| NEDg | Description generation | batch_6a05932531ec8190813d393c85d7c398 |
completed | May 14, 2026, 9:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0593b4c6b0819094d267c568332250 |
completed | May 14, 2026, 9:19 a.m. |
Created at: April 10, 2026, 11:58 a.m.