Triple
T18461947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savannah Phillips |
E451058
|
entity |
| Predicate | style |
P87
|
FINISHED |
| Object | Miss Savannah Phillips |
—
|
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: Miss Savannah Phillips | Statement: [Savannah Phillips, style, Miss Savannah Phillips]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miss Savannah Phillips Context triple: [Savannah Phillips, style, Miss Savannah Phillips]
-
A.
Savannah Phillips
chosen
Savannah Phillips is the eldest great-grandchild of Queen Elizabeth II and the daughter of Peter Phillips, making her a member of the British royal family.
-
B.
Hannah Phillips
Hannah Phillips is a fictional character in the Toy Story franchise, known as Sid Phillips' younger sister who briefly appears in the first film.
-
C.
Hannah Jo Phillips
Hannah Jo Phillips is the daughter of American actress Elizabeth Perkins.
-
D.
Molly Phillips
Molly Phillips is a fictional character best known as the widowed musician mother and paranormal investigator in the Disney Channel series "So Weird."
-
E.
Savannah Curtis
Savannah Curtis is a compassionate and idealistic young woman who becomes the love interest of soldier John Tyree in Nicholas Sparks' romantic drama "Dear John."
- 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_69d8d38345688190b565eac2e4cd7935 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e52a7fd9e081909bdf5c4aec2ba08d |
completed | April 19, 2026, 7:18 p.m. |
Created at: April 10, 2026, 11:33 a.m.