Triple
T23323939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Dunne |
E591235
|
entity |
| Predicate | bestFriendOf |
P8712
|
FINISHED |
| Object | Lloyd Christmas |
—
|
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: Lloyd Christmas | Statement: [Harry Dunne, bestFriendOf, Lloyd Christmas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lloyd Christmas Context triple: [Harry Dunne, bestFriendOf, Lloyd Christmas]
-
A.
Lloyd Christmas
chosen
Lloyd Christmas is the dim-witted yet endearingly optimistic best friend and road-trip companion from the comedy film "Dumb and Dumber."
-
B.
Lee Christmas
Lee Christmas is a skilled former SAS soldier and expert knife-wielding mercenary in the action film series "The Expendables."
-
C.
Harvey Grant
Harvey Grant is a former American professional basketball player who played primarily as a forward in the NBA during the late 1980s and 1990s.
-
D.
Tony Maudsley
Tony Maudsley is a British actor best known for his comedic television roles, including his long-running part as Kenneth in the sitcom "Benidorm."
-
E.
Bob Partridge
Bob Partridge is a fictional character from the political thriller television series "Condor."
- 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978731b0819090f92ef768f2a749 |
completed | April 29, 2026, 5:30 a.m. |
Created at: April 17, 2026, 5:08 p.m.