Triple
T5368319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Ustinov |
E108781
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Suzanne Cloutier
Suzanne Cloutier was a Canadian actress best known for her work in mid-20th-century European cinema, including roles in films by directors such as Orson Welles.
|
E518138
|
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 Cloutier | Statement: [Peter Ustinov, spouse, Suzanne Cloutier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzanne Cloutier Context triple: [Peter Ustinov, spouse, Suzanne Cloutier]
-
A.
Yvette Blais
Yvette Blais is a television composer best known for her work scoring the animated science fiction series "Star Trek: The Animated Series."
-
B.
Marie-France Boisselle
Marie-France Boisselle is known as the wife of American actor Fred Ward.
-
C.
Dominique Demers
Dominique Demers is a Canadian author and former journalist best known for her popular children's and young adult books, including the "Mlle Charlotte" series.
-
D.
Valerie LaPointe
Valerie LaPointe is an American storyboard artist, writer, and director best known for her story work at Pixar, including on Toy Story 4.
-
E.
Élisabeth Masse
Élisabeth Masse is a French local politician serving as the mayor of the commune of Saint-André-lez-Lille in northern France.
- 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 Cloutier Triple: [Peter Ustinov, spouse, Suzanne Cloutier]
Generated description
Suzanne Cloutier was a Canadian actress best known for her work in mid-20th-century European cinema, including roles in films by directors such as Orson Welles.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Suzanne Cloutier Target entity description: Suzanne Cloutier was a Canadian actress best known for her work in mid-20th-century European cinema, including roles in films by directors such as Orson Welles.
-
A.
Yvette Blais
Yvette Blais is a television composer best known for her work scoring the animated science fiction series "Star Trek: The Animated Series."
-
B.
Marie-France Boisselle
Marie-France Boisselle is known as the wife of American actor Fred Ward.
-
C.
Dominique Demers
Dominique Demers is a Canadian author and former journalist best known for her popular children's and young adult books, including the "Mlle Charlotte" series.
-
D.
Valerie LaPointe
Valerie LaPointe is an American storyboard artist, writer, and director best known for her story work at Pixar, including on Toy Story 4.
-
E.
Élisabeth Masse
Élisabeth Masse is a French local politician serving as the mayor of the commune of Saint-André-lez-Lille in northern France.
- 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_69bd440c77948190aad2a5f39b7b80f5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd86856f688190a34ab93619bae134 |
completed | March 20, 2026, 5:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3a94acc48190a4c0ea39c6b8a405 |
completed | March 22, 2026, 12:40 a.m. |
| NEDg | Description generation | batch_69bf3b2a1a888190b4c4191ec6b98b42 |
completed | March 22, 2026, 12:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf3b8170748190b2e7e427323d55f9 |
completed | March 22, 2026, 12:44 a.m. |
Created at: March 20, 2026, 2:02 p.m.