Triple
T6319990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hope Solo |
E141712
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jerramy Stevens |
E585373
|
NE FINISHED |
How this triple was built (2 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: Jerramy Stevens | Statement: [Hope Solo, spouse, Jerramy Stevens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jerramy Stevens Context triple: [Hope Solo, spouse, Jerramy Stevens]
-
A.
Jerramy Stevens
chosen
Jerramy Stevens is a former American football tight end who played in the NFL, primarily for the Seattle Seahawks and Tampa Bay Buccaneers.
-
B.
Jameer Nelson
Jameer Nelson is a former American NBA point guard best known for his standout collegiate career at Saint Joseph's University and his long tenure with the Orlando Magic.
-
C.
Tyus Edney
Tyus Edney is an American former professional basketball player and NCAA champion point guard best known for his clutch play at UCLA and a successful European career.
-
D.
John Jenkins
John Jenkins was a British politician who formerly served as the Member of Parliament for the Reigate constituency in the United Kingdom.
-
E.
Sean Whalen
Sean Whalen is an American character actor known for his distinctive, often quirky roles in film and television, including horror and cult favorites.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c008d13b8c8190be47d896eb735605 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c064c4ed7c8190bd066dc7cd3d1329 |
completed | March 22, 2026, 9:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c63862698c8190a23f9f228a7cc8a7 |
completed | March 27, 2026, 7:57 a.m. |
Created at: March 22, 2026, 4:29 p.m.