Triple
T21611565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marry Me (album) |
E533320
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Tommy Brown |
—
|
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: Tommy Brown | Statement: [Marry Me (album), producer, Tommy Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tommy Brown Context triple: [Marry Me (album), producer, Tommy Brown]
-
A.
Tommy Brown
chosen
Tommy Brown is an American record producer and songwriter known for his work with major pop and R&B artists such as Ariana Grande.
-
B.
Tommy Brown
Tommy Brown is a member of the Brown family, known as the uncle of LaPrincia Brown and part of the extended circle associated with singer Bobby Brown.
-
C.
Tommy Lewis
Tommy Lewis is an Australian actor best known for his acclaimed performance in the film "The Chant of Jimmie Blacksmith."
-
D.
Dawg Brown
Dawg Brown is the ruthless pirate villain in the 1995 swashbuckling adventure film "Cutthroat Island."
-
E.
Tommy McDonald
Tommy McDonald was a Hall of Fame American football wide receiver best known for his prolific career with the Philadelphia Eagles in the NFL during the late 1950s and 1960s.
- 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_69e0c46411108190bba0d4176dffc9f3 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef17e88f7081909371bc0de2147609 |
completed | April 27, 2026, 8:01 a.m. |
Created at: April 16, 2026, 6:33 p.m.