Triple
T17564886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Honey, I Shrunk the Kids |
E427784
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Matt Frewer |
—
|
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: Matt Frewer | Statement: [Honey, I Shrunk the Kids, stars, Matt Frewer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Frewer Context triple: [Honey, I Shrunk the Kids, stars, Matt Frewer]
-
A.
Matt Frewer
chosen
Matt Frewer is a Canadian-American actor and voice actor best known for his iconic role as the artificial intelligence character Max Headroom and for numerous appearances in film and television, including genre and science fiction works.
-
B.
A. J. Wells
A. J. Wells was a British information scientist known for his contributions to classification theory and information retrieval.
-
C.
Brett Keller
Brett Keller is the chief executive officer of Priceline, a major online travel booking company.
-
D.
Stan Humphries
Stan Humphries is an American economist and data scientist best known as the co-creator and former chief economist of Zillow, where he helped develop the company’s home-valuation “Zestimate” model.
-
E.
Brent Huff
Brent Huff is an American actor and director known for his roles in action and thriller films, as well as for his work in television.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592ce42c8190a54a0a328c5e8ffc |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.