Triple
T4666838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liar Liar |
E102865
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Cary Elwes |
E183563
|
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: Cary Elwes | Statement: [Liar Liar, starring, Cary Elwes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cary Elwes Context triple: [Liar Liar, starring, Cary Elwes]
-
A.
Cary Elwes
chosen
Cary Elwes is an English actor best known for his roles in films such as "The Princess Bride," "Robin Hood: Men in Tights," and "Saw."
-
B.
Tim Curry
Tim Curry is an English actor, singer, and voice artist best known for his iconic role as Dr. Frank-N-Furter in the cult classic film "The Rocky Horror Picture Show."
-
C.
Warwick Davis
Warwick Davis is an English actor best known for his roles in fantasy and science-fiction films such as "Willow," the "Harry Potter" series, and the "Star Wars" franchise.
-
D.
Cassian Elwes
Cassian Elwes is a British-born film producer and talent agent known for his work on numerous independent films and collaborations with prominent directors and actors in Hollywood.
-
E.
Ralph Macfadyen
Ralph Macfadyen is a child of British actor Matthew Macfadyen and his wife, actress Keeley Hawes.
- 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_69bd43d9cba4819086c1ab1c2d9d2133 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd633d87788190a3c8946ed6995062 |
completed | March 20, 2026, 3:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be038912488190a109d4ce624b813d |
completed | March 21, 2026, 2:33 a.m. |
Created at: March 20, 2026, 1:15 p.m.