Triple
T5557636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cocktail Time |
E145685
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Uncle Fred |
E29299
|
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: Uncle Fred | Statement: [Cocktail Time, mainCharacter, Uncle Fred]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uncle Fred Context triple: [Cocktail Time, mainCharacter, Uncle Fred]
-
A.
Uncle Fred
chosen
Uncle Fred is a mischievous, quick-witted aristocrat and recurring comic hero in P. G. Wodehouse’s humorous stories.
-
B.
Uncle Victor
Uncle Victor is a minor but memorable character in the dark comedy film "Harold and Maude," known for his eccentric and militaristic personality.
-
C.
Ralph Milbanke
Ralph Milbanke was a British aristocrat and member of the Milbanke family, notable as the father of Annabella Milbanke, the wife of poet Lord Byron.
-
D.
Uncle Henry
Uncle Henry is Dorothy Gale’s hardworking Kansas farmer uncle who appears as her guardian in L. Frank Baum’s Oz series.
-
E.
Mr. Bedford
Mr. Bedford is the pragmatic, often self-interested narrator and businessman who accompanies the eccentric scientist Cavor to the Moon in H. G. Wells’s science fiction novel "The First Men in the Moon."
- 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_69c008fcaf788190bafa02a1917ee73b |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01ffe12cc81908186f28ace0f4d82 |
completed | March 22, 2026, 4:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07d7658a481909e9e9b29df2b148e |
completed | March 22, 2026, 11:38 p.m. |
Created at: March 22, 2026, 3:36 p.m.