Triple
T14641905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perelman |
E343744
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Deborah Perelman
Deborah Perelman is an American business executive best known as the first woman to serve as CEO of Revlon.
|
E1113790
|
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: Deborah Perelman | Statement: [Perelman, hasNotableBearer, Deborah Perelman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deborah Perelman Context triple: [Perelman, hasNotableBearer, Deborah Perelman]
-
A.
Deborah Liebling
Deborah Liebling is an American television and film producer and executive known for her work on comedy projects.
-
B.
Deborah Weisman
Deborah Weisman is a member of the Weisman family, known primarily in relation to Daniel Weisman.
-
C.
Deborah Korman
Deborah Korman is the wife of the late American comedic actor Harvey Korman, known for his work on The Carol Burnett Show and in Mel Brooks films.
-
D.
Barbara Siegel
Barbara Siegel is an American author best known for co-writing numerous science fiction and fantasy novels and game-related books, often in collaboration with her husband Scott Siegel.
-
E.
Deborah Pines
Deborah Pines is an American physician and writer best known as the wife of journalist and author Tony Schwartz.
- 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: Deborah Perelman Triple: [Perelman, hasNotableBearer, Deborah Perelman]
Generated description
Deborah Perelman is an American business executive best known as the first woman to serve as CEO of Revlon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Deborah Perelman Target entity description: Deborah Perelman is an American business executive best known as the first woman to serve as CEO of Revlon.
-
A.
Deborah Liebling
Deborah Liebling is an American television and film producer and executive known for her work on comedy projects.
-
B.
Deborah Weisman
Deborah Weisman is a member of the Weisman family, known primarily in relation to Daniel Weisman.
-
C.
Deborah Korman
Deborah Korman is the wife of the late American comedic actor Harvey Korman, known for his work on The Carol Burnett Show and in Mel Brooks films.
-
D.
Barbara Siegel
Barbara Siegel is an American author best known for co-writing numerous science fiction and fantasy novels and game-related books, often in collaboration with her husband Scott Siegel.
-
E.
Deborah Pines
Deborah Pines is an American physician and writer best known as the wife of journalist and author Tony Schwartz.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4e80aa48190884bab800f357106 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde170d4a0819087caeacf39f95954 |
completed | May 8, 2026, 1:13 p.m. |
| NEDg | Description generation | batch_69fde580a8cc8190b5480271b1a06f4d |
completed | May 8, 2026, 1:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fde68f4ee08190b1ee18eaa390a8ff |
completed | May 8, 2026, 1:35 p.m. |
Created at: April 10, 2026, 1:26 a.m.