Triple
T20715776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diahann Carroll |
E509164
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Suzanne Kay
Suzanne Kay is an American writer and television producer, known as the daughter of pioneering actress and singer Diahann Carroll.
|
E1449255
|
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: Suzanne Kay | Statement: [Diahann Carroll, hasChild, Suzanne Kay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzanne Kay Context triple: [Diahann Carroll, hasChild, Suzanne Kay]
-
A.
Suzanne Chase
Suzanne Chase is known as the former wife of American comedian and actor Chevy Chase.
-
B.
Susanna Moore
Susanna Moore is an American novelist and screenwriter best known for her psychologically intense literary fiction, including the novel "In the Cut."
-
C.
Suzanne Welch
Suzanne "Suzy" Welch is an American author, television commentator, and business journalist known for her work on leadership, management, and career strategy.
-
D.
Suzanne Todd
Suzanne Todd is an American film producer known for her work on influential movies such as "Memento" and the "Austin Powers" series.
-
E.
Suzanne Scott
Suzanne Scott is an individual honored as a namesake of the Suzanne and Walter Scott Aquarium, indicating her significant personal or philanthropic connection to that institution.
- 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: Suzanne Kay Triple: [Diahann Carroll, hasChild, Suzanne Kay]
Generated description
Suzanne Kay is an American writer and television producer, known as the daughter of pioneering actress and singer Diahann Carroll.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Suzanne Kay Target entity description: Suzanne Kay is an American writer and television producer, known as the daughter of pioneering actress and singer Diahann Carroll.
-
A.
Suzanne Chase
Suzanne Chase is known as the former wife of American comedian and actor Chevy Chase.
-
B.
Susanna Moore
Susanna Moore is an American novelist and screenwriter best known for her psychologically intense literary fiction, including the novel "In the Cut."
-
C.
Suzanne Welch
Suzanne "Suzy" Welch is an American author, television commentator, and business journalist known for her work on leadership, management, and career strategy.
-
D.
Suzanne Todd
Suzanne Todd is an American film producer known for her work on influential movies such as "Memento" and the "Austin Powers" series.
-
E.
Suzanne Scott
Suzanne Scott is an individual honored as a namesake of the Suzanne and Walter Scott Aquarium, indicating her significant personal or philanthropic connection to that institution.
- 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d1f3308190ae594a5b9e4ab9d5 |
completed | April 21, 2026, 12:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08e830bdf481908a62eb5085fd7d76 |
completed | May 16, 2026, 9:57 p.m. |
| NEDg | Description generation | batch_6a08ec9fc4a48190b45848c8912e7ffb |
completed | May 16, 2026, 10:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08ed2d4a7481908f4e73c745039616 |
completed | May 16, 2026, 10:18 p.m. |
Created at: April 16, 2026, 12:15 p.m.