Triple
T8876778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Shelley |
E211305
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Shelley |
E168629
|
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: Shelley | Statement: [Mary Shelley, familyName, Shelley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shelley Context triple: [Mary Shelley, familyName, Shelley]
-
A.
Shelley
chosen
Shelley is the surname of Mary Shelley, the English novelist best known as the author of the Gothic classic "Frankenstein."
-
B.
Shelley
Shelley is a key supporting character in the psychological thriller film "Don't Worry Darling," portrayed as the elegant yet enigmatic wife of the community's leader.
-
C.
Shelley
Shelley is a small village in Suffolk, England, situated within the scenic Dedham Vale countryside.
-
D.
Shelley
Shelley is a feminine given name most famously borne by American actress Shelley Duvall, known for her distinctive roles in 1970s and 1980s films.
-
E.
Percy Bysshe Shelley
Percy Bysshe Shelley was a major English Romantic poet known for his radical political views, lyrical style, and works such as "Ozymandias" and "Prometheus Unbound."
- 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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61472cc081909e51b4a35a20ef43 |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfaba6f2f481909a30f71e96bc9079 |
completed | April 3, 2026, 11:59 a.m. |
Created at: March 30, 2026, 6:52 p.m.