Triple
T21743381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shep Gordon |
E536721
|
entity |
| Predicate | hasClient |
P734
|
FINISHED |
| Object | Mark Miller |
—
|
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 Miller | Statement: [Shep Gordon, hasClient, Mark Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Miller Context triple: [Shep Gordon, hasClient, Mark Miller]
-
A.
Mark Miller
Mark Miller is a professional motorcycle road racer best known for his performances in international road racing events such as the Isle of Man TT.
-
B.
Mark Miller
Mark Miller is an American actor and screenwriter known for his work in film and television from the mid-20th century onward.
-
C.
Nick Miller
Nick Miller is a gruff yet endearing, underachieving bartender and aspiring writer who serves as one of the central roommates and comedic leads in the sitcom "New Girl."
-
D.
Mark Jeffrey Miller
Mark Jeffrey Miller is an actor known for his role in the television series "Outsiders."
-
E.
Matt Miller
Matt Miller is a television writer and producer best known for creating the comedy series "Trial & Error."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a74592c8190959af631d72df479 |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 16, 2026, 6:49 p.m.