Triple
T15682134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caddyshack II |
E377602
|
entity |
| Predicate | characterInFilm |
P12208
|
FINISHED |
| Object | Ty Webb |
E377597
|
NE FINISHED |
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: Ty Webb | Statement: [Caddyshack II, characterInFilm, Ty Webb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ty Webb Context triple: [Caddyshack II, characterInFilm, Ty Webb]
-
A.
Ty Webb
chosen
Ty Webb is a laid-back, eccentric and philosophically minded golfer portrayed by Chevy Chase in the comedy film "Caddyshack."
-
B.
Steve Tumlin
Steve Tumlin is an American politician who serves as the mayor of Marietta, Georgia.
-
C.
Travis Beacham
Travis Beacham is an American screenwriter best known for co-writing the science fiction monster film "Pacific Rim."
-
D.
Mark Webley
Mark Webley is a British video game designer and producer best known as a co-founder of Lionhead Studios and his work on influential titles like Black & White and Fable.
-
E.
Reid Wiseman
Reid Wiseman is a NASA astronaut and former Chief of the Astronaut Office who has flown to the International Space Station and is slated to command the Artemis II lunar mission.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f306a1c8190a819541a3cc51f5a |
completed | April 16, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82ebe98481908d528d2cba485de4 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:16 a.m.