Triple
T19998701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MythBusters |
E494262
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Adam Savage |
—
|
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: Adam Savage | Statement: [MythBusters, castMember, Adam Savage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Savage Context triple: [MythBusters, castMember, Adam Savage]
-
A.
Adam Savage
chosen
Adam Savage is an American special effects designer, maker, and television personality best known as a co-host of the science entertainment show MythBusters.
-
B.
Jamie Hyneman
Jamie Hyneman is a special effects expert and television personality best known as one of the co-hosts of the science entertainment show MythBusters.
-
C.
Grant Imahara
Grant Imahara was an American electrical engineer, roboticist, and television host best known for designing and building robots and gadgets on the science entertainment show MythBusters.
-
D.
Michael Stevens
Michael Stevens is an American composer and musician best known for co-composing the score to the film "Invictus" alongside Kyle Eastwood.
-
E.
Mike Rowe
Mike Rowe is an American television host and narrator best known for highlighting tough, messy, and overlooked occupations and advocating for skilled trades.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a09bdc819083305b08a11c6e34 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:32 p.m.