Triple
T9754770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russell |
E236526
|
entity |
| Predicate | companionOf |
P22642
|
FINISHED |
| Object | Carl Fredricksen |
E236525
|
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: Carl Fredricksen | Statement: [Russell, companionOf, Carl Fredricksen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carl Fredricksen Context triple: [Russell, companionOf, Carl Fredricksen]
-
A.
Carl Fredricksen
chosen
Carl Fredricksen is the elderly, widowed former balloon salesman who embarks on an adventurous journey to South America in Pixar's animated film "Up."
-
B.
George Land
George Land is the largest island in the remote Arctic archipelago of Franz Josef Land in northern Russia.
-
C.
Woodie
Woodie is a central character known for embodying the laid-back, carefree spirit associated with "good vibes."
-
D.
Elwood P. Dowd
Elwood P. Dowd is the amiable, eccentric protagonist of the play and film "Harvey," known for his unwavering friendship with an invisible six-foot-tall rabbit.
-
E.
Irwin Keyes
Irwin Keyes was an American character actor best known for his imposing physique and roles in films and TV shows such as "The Jeffersons" and various horror and comedy movies.
- 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_69ca84d4eddc8190996fec1417d2bae8 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9fb1370c8190bc153db8cababc62 |
completed | April 1, 2026, 10:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1bcd60e1c81908ea2e38ca91e58f6 |
completed | April 5, 2026, 1:37 a.m. |
Created at: March 30, 2026, 8:24 p.m.