Triple
T16459727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University High School, Irvine |
E399774
|
entity |
| Predicate | hasAlumni |
P51
|
FINISHED |
| Object |
Brandon Hagy
Brandon Hagy is an American professional golfer who has competed on the PGA Tour.
|
E1218623
|
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: Brandon Hagy | Statement: [University High School, Irvine, hasAlumni, Brandon Hagy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brandon Hagy Context triple: [University High School, Irvine, hasAlumni, Brandon Hagy]
-
A.
Jonathan Zebina
Jonathan Zebina is a retired French professional footballer best known as a strong, versatile defender who played for clubs such as AS Roma and Juventus in Serie A.
-
B.
Max Malkin
Max Malkin is a cinematographer best known for his work on the dance film "Step Up 2: The Streets."
-
C.
Brook Doan
Brook Doan is a member of the Doan family, known primarily as the sibling of former NHL star Shane Doan.
-
D.
Jason Filardi
Jason Filardi is an American screenwriter best known for writing popular Hollywood comedies, including the hit film "Bringing Down the House."
-
E.
John Matsko
John Matsko is an American football offensive line coach best known for his long NFL coaching career with multiple teams, including the St. Louis Rams during their high-powered "Greatest Show on Turf" era.
- 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: Brandon Hagy Triple: [University High School, Irvine, hasAlumni, Brandon Hagy]
Generated description
Brandon Hagy is an American professional golfer who has competed on the PGA Tour.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brandon Hagy Target entity description: Brandon Hagy is an American professional golfer who has competed on the PGA Tour.
-
A.
Jonathan Zebina
Jonathan Zebina is a retired French professional footballer best known as a strong, versatile defender who played for clubs such as AS Roma and Juventus in Serie A.
-
B.
Max Malkin
Max Malkin is a cinematographer best known for his work on the dance film "Step Up 2: The Streets."
-
C.
Brook Doan
Brook Doan is a member of the Doan family, known primarily as the sibling of former NHL star Shane Doan.
-
D.
Jason Filardi
Jason Filardi is an American screenwriter best known for writing popular Hollywood comedies, including the hit film "Bringing Down the House."
-
E.
John Matsko
John Matsko is an American football offensive line coach best known for his long NFL coaching career with multiple teams, including the St. Louis Rams during their high-powered "Greatest Show on Turf" era.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32d7ff0e881909100bb5b33c04291 |
completed | April 18, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00607618c8819090fc9f18ae5f30dd |
completed | May 10, 2026, 10:39 a.m. |
| NEDg | Description generation | batch_6a0061e33a508190b5f2ecdac51d79bc |
completed | May 10, 2026, 10:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0062665d908190b8127b21edcad30e |
completed | May 10, 2026, 10:48 a.m. |
Created at: April 10, 2026, 5:10 a.m.