Triple
T10605028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Roy |
E275849
|
entity |
| Predicate | hasRomanticRelationshipWith |
P9994
|
FINISHED |
| Object |
Gerri Kellman
Gerri Kellman is a high-ranking legal executive and trusted advisor within the Roy family’s media empire in the television series "Succession."
|
E902605
|
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: Gerri Kellman | Statement: [Roman Roy, hasRomanticRelationshipWith, Gerri Kellman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gerri Kellman Context triple: [Roman Roy, hasRomanticRelationshipWith, Gerri Kellman]
-
A.
Jill Krementz
Jill Krementz is an American photographer and author best known for her portraits of writers and her work in children's literature.
-
B.
Diane Siegler
Diane Siegler is a character in the satirical film "Citizen Ruth," which critiques the abortion debate in the United States.
-
C.
Gail Katz
Gail Katz is an American film and television producer known for working on major Hollywood projects including the disaster drama "The Perfect Storm."
-
D.
Arlene Litman
Arlene Litman was the mother of American actress Lisa Bonet.
-
E.
Lorraine Bergman
Lorraine Bergman was the wife of American physicist and Nobel laureate Carl David Anderson.
- 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: Gerri Kellman Triple: [Roman Roy, hasRomanticRelationshipWith, Gerri Kellman]
Generated description
Gerri Kellman is a high-ranking legal executive and trusted advisor within the Roy family’s media empire in the television series "Succession."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gerri Kellman Target entity description: Gerri Kellman is a high-ranking legal executive and trusted advisor within the Roy family’s media empire in the television series "Succession."
-
A.
Jill Krementz
Jill Krementz is an American photographer and author best known for her portraits of writers and her work in children's literature.
-
B.
Diane Siegler
Diane Siegler is a character in the satirical film "Citizen Ruth," which critiques the abortion debate in the United States.
-
C.
Gail Katz
Gail Katz is an American film and television producer known for working on major Hollywood projects including the disaster drama "The Perfect Storm."
-
D.
Arlene Litman
Arlene Litman was the mother of American actress Lisa Bonet.
-
E.
Lorraine Bergman
Lorraine Bergman was the wife of American physicist and Nobel laureate Carl David Anderson.
- 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6df4a5df88190b993196ca7849a88 |
completed | April 8, 2026, 11:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3c7b89a808190af9b2d4f37ad9012 |
completed | April 18, 2026, 6:04 p.m. |
| NEDg | Description generation | batch_69e3cefc00148190a1850dc6e31523c3 |
completed | April 18, 2026, 6:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e3d014a644819092c76aa02b573ca9 |
completed | April 18, 2026, 6:40 p.m. |
Created at: April 8, 2026, 7:32 p.m.