Triple
T4250468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat LaFontaine |
E95835
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
LaFontaine
LaFontaine is a surname most prominently associated with Pat LaFontaine, a Hall of Fame American ice hockey player known for his prolific NHL scoring career.
|
E424441
|
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: LaFontaine | Statement: [Pat LaFontaine, familyName, LaFontaine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LaFontaine Context triple: [Pat LaFontaine, familyName, LaFontaine]
-
A.
Desmarais
Desmarais is a French surname, often associated with notable families and individuals in business, politics, and the arts.
-
B.
Nézet-Séguin
Nézet-Séguin is the hyphenated family name of Canadian conductor Yannick Nézet-Séguin, renowned for his leadership of major orchestras and opera companies.
-
C.
Duplessis
Duplessis is a surname of French origin borne by various notable individuals in politics, sports, and the arts.
-
D.
Géo Lefèvre
Géo Lefèvre was a French sports journalist best known for conceiving the idea of the Tour de France while working for the newspaper L’Auto.
-
E.
Guillaume Laforge
Guillaume Laforge is a French software engineer best known as the longtime project lead and advocate of the Groovy programming language.
- 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: LaFontaine Triple: [Pat LaFontaine, familyName, LaFontaine]
Generated description
LaFontaine is a surname most prominently associated with Pat LaFontaine, a Hall of Fame American ice hockey player known for his prolific NHL scoring career.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LaFontaine Target entity description: LaFontaine is a surname most prominently associated with Pat LaFontaine, a Hall of Fame American ice hockey player known for his prolific NHL scoring career.
-
A.
Desmarais
Desmarais is a French surname, often associated with notable families and individuals in business, politics, and the arts.
-
B.
Nézet-Séguin
Nézet-Séguin is the hyphenated family name of Canadian conductor Yannick Nézet-Séguin, renowned for his leadership of major orchestras and opera companies.
-
C.
Duplessis
Duplessis is a surname of French origin borne by various notable individuals in politics, sports, and the arts.
-
D.
Géo Lefèvre
Géo Lefèvre was a French sports journalist best known for conceiving the idea of the Tour de France while working for the newspaper L’Auto.
-
E.
Guillaume Laforge
Guillaume Laforge is a French software engineer best known as the longtime project lead and advocate of the Groovy programming language.
- 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_69b3453f759881909b91f01a1e82c036 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e9f11008190a0021e0ad730a79d |
completed | March 12, 2026, 11:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a88225288190bb627de15da77c42 |
completed | March 14, 2026, 6:27 p.m. |
| NEDg | Description generation | batch_69b5a959f3f08190af8b7b87afe15a54 |
completed | March 14, 2026, 6:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5ad13d2988190bc43050ac73919fa |
completed | March 14, 2026, 6:46 p.m. |
Created at: March 12, 2026, 11:06 p.m.