Triple
T10323081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Believer |
E242688
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Susan Hoffman
Susan Hoffman is a film producer known for her work on the psychological drama "The Believer."
|
E869590
|
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: Susan Hoffman | Statement: [The Believer, producer, Susan Hoffman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Hoffman Context triple: [The Believer, producer, Susan Hoffman]
-
A.
Susan Weiler
Susan Weiler is a prominent landscape architect and design leader known for her influential work with the firm OLIN on major public and urban spaces.
-
B.
Susan Lindauer
Susan Lindauer is an American former journalist and antiwar activist best known for her controversial claims of having served as a back-channel intermediary to Iraq and for being one of the first people charged under the U.S. Patriot Act.
-
C.
Susan Hilferty
Susan Hilferty is a Tony Award–winning American costume designer best known for her iconic work on the Broadway musical "Wicked."
-
D.
Judy Hofflund
Judy Hofflund is a film producer known for her work on major studio projects, including the 2022 adaptation of "Death on the Nile."
-
E.
Susan Benfer
Susan Benfer is known as the wife of prominent American newscaster David Brinkley.
- 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: Susan Hoffman Triple: [The Believer, producer, Susan Hoffman]
Generated description
Susan Hoffman is a film producer known for her work on the psychological drama "The Believer."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Susan Hoffman Target entity description: Susan Hoffman is a film producer known for her work on the psychological drama "The Believer."
-
A.
Susan Weiler
Susan Weiler is a prominent landscape architect and design leader known for her influential work with the firm OLIN on major public and urban spaces.
-
B.
Susan Lindauer
Susan Lindauer is an American former journalist and antiwar activist best known for her controversial claims of having served as a back-channel intermediary to Iraq and for being one of the first people charged under the U.S. Patriot Act.
-
C.
Susan Hilferty
Susan Hilferty is a Tony Award–winning American costume designer best known for her iconic work on the Broadway musical "Wicked."
-
D.
Judy Hofflund
Judy Hofflund is a film producer known for her work on major studio projects, including the 2022 adaptation of "Death on the Nile."
-
E.
Susan Benfer
Susan Benfer is known as the wife of prominent American newscaster David Brinkley.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d6cdb6cc8190b37ca4494287128b |
completed | April 7, 2026, 10:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90d76fd88819086c61c40216a8932 |
completed | April 10, 2026, 2:47 p.m. |
| NEDg | Description generation | batch_69d91156a1b08190b5caeff755387692 |
completed | April 10, 2026, 3:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d91214c75c8190af55173325a0f409 |
completed | April 10, 2026, 3:07 p.m. |
Created at: April 6, 2026, 11:50 a.m.