Triple
T11983730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Dee Williams |
E285222
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Marlene Clark
Marlene Clark is an American actress and model best known for her roles in 1970s films such as "Ganja & Hess" and "Enter the Dragon."
|
E958240
|
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: Marlene Clark | Statement: [Billy Dee Williams, spouse, Marlene Clark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marlene Clark Context triple: [Billy Dee Williams, spouse, Marlene Clark]
-
A.
Patricia Blair
Patricia Blair was an American film and television actress best known for her roles in 1960s TV series such as "Daniel Boone" and "The Rifleman."
-
B.
Janet Turnbull
Janet Turnbull is the wife of American novelist John Irving, known for accompanying him at literary events and in public life.
-
C.
Diane Smith
Diane Smith is known as the wife of Frederick W. Smith, the founder and longtime CEO of FedEx.
-
D.
Barbara Carr
Barbara Carr is a music industry executive and longtime manager of Bruce Springsteen who co-produced his acclaimed stage production "Springsteen on Broadway."
-
E.
Patricia Rice
Patricia Rice is an American author best known for her historical and contemporary romance novels, often featuring strong heroines and elements of fantasy.
- 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: Marlene Clark Triple: [Billy Dee Williams, spouse, Marlene Clark]
Generated description
Marlene Clark is an American actress and model best known for her roles in 1970s films such as "Ganja & Hess" and "Enter the Dragon."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marlene Clark Target entity description: Marlene Clark is an American actress and model best known for her roles in 1970s films such as "Ganja & Hess" and "Enter the Dragon."
-
A.
Patricia Blair
Patricia Blair was an American film and television actress best known for her roles in 1960s TV series such as "Daniel Boone" and "The Rifleman."
-
B.
Janet Turnbull
Janet Turnbull is the wife of American novelist John Irving, known for accompanying him at literary events and in public life.
-
C.
Diane Smith
Diane Smith is known as the wife of Frederick W. Smith, the founder and longtime CEO of FedEx.
-
D.
Barbara Carr
Barbara Carr is a music industry executive and longtime manager of Bruce Springsteen who co-produced his acclaimed stage production "Springsteen on Broadway."
-
E.
Patricia Rice
Patricia Rice is an American author best known for her historical and contemporary romance novels, often featuring strong heroines and elements of fantasy.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903973c848190aac871d6dfecc74b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f472286edc8190ac72d7dd2b646c91 |
completed | May 1, 2026, 9:28 a.m. |
| NEDg | Description generation | batch_69f47b7c5af08190ab0bff1232530a0c |
completed | May 1, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f47dd51e648190bddd41766221e22d |
completed | May 1, 2026, 10:17 a.m. |
Created at: April 8, 2026, 9:46 p.m.