Triple
T19889315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dick |
E477985
|
entity |
| Predicate | hasVariantForm |
P457
|
FINISHED |
| Object | Dickie |
—
|
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: Dickie | Statement: [Dick, hasVariantForm, Dickie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dickie Context triple: [Dick, hasVariantForm, Dickie]
-
A.
Dickie
Dickie is a Scottish surname most notably associated with actress Kate Dickie, known for her roles in film and television.
-
B.
Dicky
chosen
Dicky is a diminutive given name or nickname, typically used as a familiar form of the name Richard.
-
C.
Dickie V
Dickie V is the exuberant, catchphrase-spouting American college basketball broadcaster and former coach best known for his long tenure as an ESPN analyst.
-
D.
Dickie Jones
Dickie Jones was an American child actor best known as the voice of the title character in Disney’s 1940 animated film "Pinocchio."
-
E.
Dickie Winslow
Dickie Winslow is a fictional member of the Winslow family in the play and film adaptations of "The Winslow Boy," related to Ronnie Winslow.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590ce9f48190a51c0e5ecc828a06 |
completed | April 20, 2026, 4:49 p.m. |
Created at: April 10, 2026, 1:52 p.m.