Triple
T10812464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kings Row |
E255136
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Ralph Dawson |
E162172
|
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 Dawson | Statement: [Kings Row, editedBy, Ralph Dawson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ralph Dawson Context triple: [Kings Row, editedBy, Ralph Dawson]
-
A.
Ralph Dawson
chosen
Ralph Dawson was an American film editor known for his work on numerous Hollywood productions during the early 20th century.
-
B.
Ralph Furley
Ralph Furley is the flamboyantly dressed, bumbling landlord character from the sitcom "Three's Company," known for his exaggerated reactions and comic misunderstandings.
-
C.
Ralph Simpson
Ralph Simpson is a former professional basketball guard best known for his high-scoring play in the American Basketball Association during the early 1970s.
-
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 Thomas
Ralph Thomas is the son of British film producer Jeremy Thomas.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733eadda48190b2b1183ee60102cb |
completed | April 9, 2026, 5:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e8a68e4404819096c5023c7eca4b6a |
completed | April 22, 2026, 10:44 a.m. |
Created at: April 8, 2026, 9:18 p.m.