Triple
T2216132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Bob Thornton |
E48035
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Toni Lawrence
Toni Lawrence is an American actress known for her film and television work in the 1970s and 1980s.
|
E289031
|
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: Toni Lawrence | Statement: [Billy Bob Thornton, spouse, Toni Lawrence]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toni Lawrence Context triple: [Billy Bob Thornton, spouse, Toni Lawrence]
-
A.
Marli Bennett
Marli Bennett is the daughter of American rapper and musician Chance the Rapper (Chancelor Bennett).
-
B.
Diandra Luker
Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
-
C.
Joanne Tucker
Joanne Tucker is an American actress known for her work in independent films and theater, as well as for her involvement in arts-focused nonprofit initiatives.
-
D.
Wendy Lawrence
Wendy Lawrence is a retired U.S. Navy captain and NASA astronaut who flew on multiple Space Shuttle missions as a mission specialist.
-
E.
Katherine Rogers
Katherine Rogers was the mother of John Harvard, the English clergyman whose bequest helped found Harvard College in colonial Massachusetts.
- 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: Toni Lawrence Triple: [Billy Bob Thornton, spouse, Toni Lawrence]
Generated description
Toni Lawrence is an American actress known for her film and television work in the 1970s and 1980s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Toni Lawrence Target entity description: Toni Lawrence is an American actress known for her film and television work in the 1970s and 1980s.
-
A.
Marli Bennett
Marli Bennett is the daughter of American rapper and musician Chance the Rapper (Chancelor Bennett).
-
B.
Diandra Luker
Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
-
C.
Joanne Tucker
Joanne Tucker is an American actress known for her work in independent films and theater, as well as for her involvement in arts-focused nonprofit initiatives.
-
D.
Wendy Lawrence
Wendy Lawrence is a retired U.S. Navy captain and NASA astronaut who flew on multiple Space Shuttle missions as a mission specialist.
-
E.
Katherine Rogers
Katherine Rogers was the mother of John Harvard, the English clergyman whose bequest helped found Harvard College in colonial Massachusetts.
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc00f4c3881909d03301fcdfa8b67 |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa03c35f48190a4ad11595fea91ae |
completed | March 10, 2026, 4:38 a.m. |
| NEDg | Description generation | batch_69afa24054f48190a7af299c72962b3b |
completed | March 10, 2026, 4:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69afa2da7cc88190a9568cd573ce5b41 |
completed | March 10, 2026, 4:49 a.m. |
Created at: March 4, 2026, 7:46 p.m.