Triple
T8275382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Hasselbeck |
E193533
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object |
Tim Hasselbeck
Tim Hasselbeck is a former NFL quarterback who later became a football analyst and commentator for ESPN.
|
E731128
|
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: Tim Hasselbeck | Statement: [Matt Hasselbeck, sibling, Tim Hasselbeck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tim Hasselbeck Context triple: [Matt Hasselbeck, sibling, Tim Hasselbeck]
-
A.
Sarah Hasselbeck
Sarah Hasselbeck is known as the wife of former NFL quarterback and sports analyst Matt Hasselbeck.
-
B.
Matt Hasselbeck
Matt Hasselbeck is a former NFL quarterback best known for leading the Seattle Seahawks to multiple playoff appearances and a Super Bowl berth in the 2000s.
-
C.
Brian Griese
Brian Griese is a former American NFL quarterback who played primarily for the Denver Broncos and later became a football analyst and coach.
-
D.
Drew Bledsoe
Drew Bledsoe is a former NFL quarterback best known for his long tenure with the New England Patriots and for paving the way for Tom Brady’s rise after Bledsoe’s injury.
-
E.
Trent Dilfer
Trent Dilfer is a former NFL quarterback best known for leading the Baltimore Ravens to a championship in Super Bowl XXXV and later working as a football analyst and college coach.
- 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: Tim Hasselbeck Triple: [Matt Hasselbeck, sibling, Tim Hasselbeck]
Generated description
Tim Hasselbeck is a former NFL quarterback who later became a football analyst and commentator for ESPN.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tim Hasselbeck Target entity description: Tim Hasselbeck is a former NFL quarterback who later became a football analyst and commentator for ESPN.
-
A.
Sarah Hasselbeck
Sarah Hasselbeck is known as the wife of former NFL quarterback and sports analyst Matt Hasselbeck.
-
B.
Matt Hasselbeck
Matt Hasselbeck is a former NFL quarterback best known for leading the Seattle Seahawks to multiple playoff appearances and a Super Bowl berth in the 2000s.
-
C.
Brian Griese
Brian Griese is a former American NFL quarterback who played primarily for the Denver Broncos and later became a football analyst and coach.
-
D.
Drew Bledsoe
Drew Bledsoe is a former NFL quarterback best known for his long tenure with the New England Patriots and for paving the way for Tom Brady’s rise after Bledsoe’s injury.
-
E.
Trent Dilfer
Trent Dilfer is a former NFL quarterback best known for leading the Baltimore Ravens to a championship in Super Bowl XXXV and later working as a football analyst and college coach.
- 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb798bc29c8190927ef4b0662d6b98 |
completed | March 31, 2026, 7:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce025db14881909124c1398d5f7d4a |
completed | April 2, 2026, 5:45 a.m. |
| NEDg | Description generation | batch_69ce077d8af0819082a7ea67a2c11ddd |
completed | April 2, 2026, 6:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce082078108190867044f45bc0a806 |
completed | April 2, 2026, 6:09 a.m. |
Created at: March 30, 2026, 5:51 p.m.