Triple
T36407052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Walton's ship |
E896774
|
entity |
| Predicate | authorWorkOfAppearance |
P110113
|
FINISHED |
| Object | Mary Shelley |
—
|
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: Mary Shelley | Statement: [Robert Walton's ship, authorWorkOfAppearance, Mary Shelley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorWorkOfAppearance Context triple: [Robert Walton's ship, authorWorkOfAppearance, Mary Shelley]
-
A.
authorOfWorkAppearingIn
chosen
Indicates that one entity is the creator or writer of a work that appears within another work or publication.
-
B.
appearsInWorkByAuthorFrom
Indicates that an entity appears in a work that was created by an author originating from a specified place or country.
-
C.
creatorOfWorkAppearedIn
Indicates that a person is the creator (e.g., author, artist, director) of a work in which a given entity appeared.
-
D.
workAppearedInAuthor
Indicates that a particular work by an author appeared in or was included within another creator’s authored work (e.g., as a contribution, feature, or inclusion).
-
E.
authorOfWorkHeAppearsIn
Indicates that a person is the author of a work in which he himself appears as a character or subject.
- F. None of above.
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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe5c1a502081909d4024e514309c8e |
completed | May 8, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69fe5a9df21c819087153f5d0bcaa987 |
completed | May 8, 2026, 9:50 p.m. |
Created at: May 3, 2026, 4:10 p.m.