Triple
T23511866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Kelso |
E572446
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Mark Brazill |
—
|
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: Mark Brazill | Statement: [Michael Kelso, createdBy, Mark Brazill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Brazill Context triple: [Michael Kelso, createdBy, Mark Brazill]
-
A.
Mark Brazill
chosen
Mark Brazill is an American television writer and producer best known for co-creating the hit sitcom That '70s Show.
-
B.
Brian Andrews
Brian Andrews is a songwriter best known for his work on the track "Got Me Going."
-
C.
Andrew Morgan
Andrew Morgan is a British television director best known for his work on the classic science fiction series Doctor Who.
-
D.
Andrew Morgan
Andrew Morgan is a filmmaker best known for directing the documentary "The True Cost," which examines the global impact of the fast fashion industry.
-
E.
Scott Morgan
Scott Morgan is a name shared by several notable individuals, including athletes, musicians, and public figures across different fields.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa7f583881909e78e8fe2e6e25fe |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:07 p.m.