Triple
T14843249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perri |
E349019
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Ralph Wright |
E1020227
|
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: Ralph Wright | Statement: [Perri, director, Ralph Wright]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ralph Wright Context triple: [Perri, director, Ralph Wright]
-
A.
Ralph Wright
chosen
Ralph Wright was an American animator and writer best known for his story and screenwriting work on numerous classic Disney films.
-
B.
Ralph Walker
Ralph Walker was a British civil engineer and architect known for his influential work on major dock projects in London during the late 18th and early 19th centuries.
-
C.
Ralph Walker
Ralph Walker was a prominent early 20th-century American architect known for his influential Art Deco skyscraper designs in New York City.
-
D.
Ralph Partridge
Ralph Partridge was an English editor and member of the Bloomsbury Group, closely associated with figures like Lytton Strachey and Dora Carrington.
-
E.
Ralph Hart
Ralph Hart is an actor best known for his role on the classic American television sitcom "The Lucy Show."
- 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_69d822ec69008190a9232caa68836872 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded28fa49c81908d1059e6cafd607f |
completed | April 14, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec870cea08190962434fc2647fd67 |
completed | May 9, 2026, 5:38 a.m. |
Created at: April 10, 2026, 1:53 a.m.