Triple
T6197369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vincent Lindon |
E138541
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Marcel Lindon
Marcel Lindon is the son of French actor Vincent Lindon.
|
E574928
|
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: Marcel Lindon | Statement: [Vincent Lindon, hasChild, Marcel Lindon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcel Lindon Context triple: [Vincent Lindon, hasChild, Marcel Lindon]
-
A.
Henry Gibson
Henry Gibson was an American character actor and comedian known for his work on the sketch comedy show "Rowan & Martin's Laugh-In" and in numerous film and television roles.
-
B.
Lewis Stevenson
Lewis Stevenson was an American politician and public servant from Illinois, known as a prominent member of the influential Stevenson political family.
-
C.
Alan Baxter
Alan Baxter was an American character actor known for his roles in mid-20th-century film and television, often portraying tough or villainous figures.
-
D.
Felix Aylmer
Felix Aylmer was a distinguished English character actor known for his refined, often authoritative roles in British stage and film productions of the mid-20th century.
-
E.
Dudley Nichols
Dudley Nichols was an American screenwriter and director best known for his prolific work in Hollywood’s Golden Age, including his Academy Award-winning script for "The Informer."
- 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: Marcel Lindon Triple: [Vincent Lindon, hasChild, Marcel Lindon]
Generated description
Marcel Lindon is the son of French actor Vincent Lindon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marcel Lindon Target entity description: Marcel Lindon is the son of French actor Vincent Lindon.
-
A.
Henry Gibson
Henry Gibson was an American character actor and comedian known for his work on the sketch comedy show "Rowan & Martin's Laugh-In" and in numerous film and television roles.
-
B.
Lewis Stevenson
Lewis Stevenson was an American politician and public servant from Illinois, known as a prominent member of the influential Stevenson political family.
-
C.
Alan Baxter
Alan Baxter was an American character actor known for his roles in mid-20th-century film and television, often portraying tough or villainous figures.
-
D.
Felix Aylmer
Felix Aylmer was a distinguished English character actor known for his refined, often authoritative roles in British stage and film productions of the mid-20th century.
-
E.
Dudley Nichols
Dudley Nichols was an American screenwriter and director best known for his prolific work in Hollywood’s Golden Age, including his Academy Award-winning script for "The Informer."
- 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_69c008ab9b3081908a11b2c744838435 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062508f5c8190a00291708a9a7de9 |
completed | March 22, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c16f2a40a88190847f607a6e2c5f4e |
completed | March 23, 2026, 4:49 p.m. |
| NEDg | Description generation | batch_69c1d232ab1881909cc3014beb664446 |
completed | March 23, 2026, 11:52 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c1d2c532988190a98f615638987159 |
completed | March 23, 2026, 11:54 p.m. |
Created at: March 22, 2026, 4:20 p.m.