Triple
T13761830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Brady Sr. |
E330628
|
entity |
| Predicate | hasDaughter |
P24357
|
FINISHED |
| Object | Julie Brady |
E1062743
|
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: Julie Brady | Statement: [Tom Brady Sr., hasDaughter, Julie Brady]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julie Brady Context triple: [Tom Brady Sr., hasDaughter, Julie Brady]
-
A.
Julie Brady
chosen
Julie Brady is an American woman best known as the sister of NFL quarterback Tom Brady and the daughter of Galynn and Tom Brady Sr.
-
B.
Jennifer Brady
Jennifer Brady is an American professional tennis player known for her powerful baseline game and breakthrough run to the 2021 Australian Open final.
-
C.
Julie Thompson
Julie Thompson is the mother of NBA star Klay Thompson and part of the Thompson family known for its strong basketball legacy.
-
D.
Julie Wright
Julie Wright is known as the spouse of American character actor Pat Hingle, who appeared in numerous films, television shows, and stage productions.
-
E.
Renee Bartlett
Renee Bartlett was the wife of acclaimed Austrian-American film director Fred Zinnemann.
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02250f4881908d5193b3d5d25844 |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0ded1e0819097ef42533357caf8 |
completed | May 3, 2026, 9:40 p.m. |
Created at: April 9, 2026, 10:09 p.m.