Triple
T16047337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Green |
E389257
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object |
Paul Gregory Green
Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
|
E1190836
|
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: Paul Gregory Green | Statement: [Paul Green, fullName, Paul Gregory Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Gregory Green Context triple: [Paul Green, fullName, Paul Gregory Green]
-
A.
Christopher Greenup
Christopher Greenup was an early American politician who served as the third governor of Kentucky in the early 19th century.
-
B.
Paul Greer
Paul Greer is a person notable enough to be specifically distinguished among individuals sharing the surname Greer.
-
C.
Richard Green
Richard Green was an American boxing referee best known for officiating major heavyweight bouts, including the 1980 title fight between Larry Holmes and Muhammad Ali.
-
D.
Christopher Greenbury
Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
-
E.
Andrew Green
Andrew Green was a British paranormal investigator and author known for his extensive work on ghost hunting and psychical research.
- 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: Paul Gregory Green Triple: [Paul Green, fullName, Paul Gregory Green]
Generated description
Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paul Gregory Green Target entity description: Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
-
A.
Christopher Greenup
Christopher Greenup was an early American politician who served as the third governor of Kentucky in the early 19th century.
-
B.
Paul Greer
Paul Greer is a person notable enough to be specifically distinguished among individuals sharing the surname Greer.
-
C.
Richard Green
Richard Green was an American boxing referee best known for officiating major heavyweight bouts, including the 1980 title fight between Larry Holmes and Muhammad Ali.
-
D.
Christopher Greenbury
Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
-
E.
Andrew Green
Andrew Green was a British paranormal investigator and author known for his extensive work on ghost hunting and psychical research.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1835eda348190aff492f0ff668cce |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbddc25481908fca660c4f14eaff |
completed | May 10, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_69ffdc915be88190a0e949fcee608242 |
completed | May 10, 2026, 1:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffdd17239c8190a3c0c4d146a279f7 |
completed | May 10, 2026, 1:19 a.m. |
Created at: April 10, 2026, 4:56 a.m.