Triple
T22725089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sammy Bryant |
E561968
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Tammi Bryant |
—
|
NE NERFINISHED |
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: Tammi Bryant | Statement: [Sammy Bryant, spouse, Tammi Bryant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tammi Bryant Context triple: [Sammy Bryant, spouse, Tammi Bryant]
-
A.
Tammi Bryant
chosen
Tammi Bryant is a professional colleague of Sammy Bryant, likely working in the same or a closely related field.
-
B.
Tammi
Tammi is a Finnish publishing house known for releasing notable works of literature, including the Finnish editions of the Moomin books.
-
C.
Brenda Malone
Brenda Malone is a notable individual recognized for achievements significant enough to be distinctly associated with the surname Malone.
-
D.
Teresa Carpenter
Teresa Carpenter is a Pulitzer Prize–winning American journalist and author known for her incisive true-crime and narrative nonfiction writing.
-
E.
Tina Templeton
Tina Templeton is the spirited, secret-agent baby sister who plays a central role in the animated film "The Boss Baby: Family Business."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17928a21c8190a1b888754ba7808b |
completed | April 29, 2026, 3:21 a.m. |
Created at: April 17, 2026, 3:20 p.m.