Triple
T20360750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Summer Story |
E496771
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Sophie Ward |
—
|
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: Sophie Ward | Statement: [A Summer Story, stars, Sophie Ward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sophie Ward Context triple: [A Summer Story, stars, Sophie Ward]
-
A.
Sophie Ward
chosen
Sophie Ward is an English actress and writer known for her roles in film and television, including her early performance in "Young Sherlock Holmes."
-
B.
Sophie Earl
Sophie Earl is the daughter of film and television director Rachel Talalay.
-
C.
Sophie Menter
Sophie Menter was a renowned 19th-century German pianist and composer celebrated for her virtuosic performances and close artistic association with Franz Liszt.
-
D.
Sophie Straw
Sophie Straw is the charismatic, working-class young woman who becomes a groundbreaking television comedy star in Nick Hornby’s novel "Funny Girl."
-
E.
Sophie Raworth
Sophie Raworth is a British journalist and newsreader best known as one of the main presenters of BBC News.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678584294819093788ccf2fb8e588 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.