Triple
T20241865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Free Willy 3: The Rescue |
E498315
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | John Mattson |
—
|
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: John Mattson | Statement: [Free Willy 3: The Rescue, writer, John Mattson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Mattson Context triple: [Free Willy 3: The Rescue, writer, John Mattson]
-
A.
John Mattson
chosen
John Mattson is an American screenwriter best known for his work on the 1994 family comedy film "Milk Money."
-
B.
Brian Swardstrom
Brian Swardstrom is a prominent American talent agent and partner at United Talent Agency, known for representing acclaimed actors and filmmakers.
-
C.
Kevin Hageman
Kevin Hageman is an American screenwriter and producer known for his work on animated and family films and television series, including contributions to The Lego Movie franchise.
-
D.
John Crouse
John Crouse was a prominent member of the Lindsay and Crouse family, known for his role in their business and social prominence.
-
E.
Andrew Mittman
Andrew Mittman is a television and film producer known for his executive production work on series such as the Netflix show "Wednesday."
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716f9d248190a145f6883827ebbe |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.