Triple
T1578603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Donovan |
E33709
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Bryan Donovan
Bryan Donovan is one of the children of American basketball coach Billy Donovan.
|
E188622
|
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: Bryan Donovan | Statement: [Billy Donovan, hasChild, Bryan Donovan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bryan Donovan Context triple: [Billy Donovan, hasChild, Bryan Donovan]
-
A.
Brendan Rogers
Brendan Rogers is a Northern Irish football manager and former player best known for managing clubs such as Liverpool, Celtic, and Leicester City.
-
B.
Eric Mangini
Eric Mangini is an American football coach best known for serving as head coach of the New York Jets and Cleveland Browns in the NFL.
-
C.
Eric DeCosta
Eric DeCosta is an American football executive who serves as the general manager of the NFL's Baltimore Ravens, overseeing the team's roster construction and football operations.
-
D.
Rick Hahn
Rick Hahn is an American baseball executive best known for serving as the general manager of the Chicago White Sox in Major League Baseball.
-
E.
Tony DiCicco
Tony DiCicco was an American soccer coach best known for leading the U.S. women’s national team to victory in the 1996 Olympics and the 1999 FIFA Women’s World Cup.
- 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: Bryan Donovan Triple: [Billy Donovan, hasChild, Bryan Donovan]
Generated description
Bryan Donovan is one of the children of American basketball coach Billy Donovan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bryan Donovan Target entity description: Bryan Donovan is one of the children of American basketball coach Billy Donovan.
-
A.
Brendan Rogers
Brendan Rogers is a Northern Irish football manager and former player best known for managing clubs such as Liverpool, Celtic, and Leicester City.
-
B.
Eric Mangini
Eric Mangini is an American football coach best known for serving as head coach of the New York Jets and Cleveland Browns in the NFL.
-
C.
Eric DeCosta
Eric DeCosta is an American football executive who serves as the general manager of the NFL's Baltimore Ravens, overseeing the team's roster construction and football operations.
-
D.
Rick Hahn
Rick Hahn is an American baseball executive best known for serving as the general manager of the Chicago White Sox in Major League Baseball.
-
E.
Tony DiCicco
Tony DiCicco was an American soccer coach best known for leading the U.S. women’s national team to victory in the 1996 Olympics and the 1999 FIFA Women’s World Cup.
- 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_69a885f27a4c8190a4622252cdf54c00 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a908d67bd08190afa8c504ed5273ee |
completed | March 5, 2026, 4:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad680b40908190acf505992848dae9 |
completed | March 8, 2026, 12:14 p.m. |
| NEDg | Description generation | batch_69ad6c05c69c81908969384b352d3151 |
completed | March 8, 2026, 12:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad6c9596508190aed71ef5b3a2092a |
completed | March 8, 2026, 12:33 p.m. |
Created at: March 4, 2026, 7:27 p.m.