Triple
T37037904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Treason of Isengard |
E916696
|
entity |
| Predicate | mainSubjectAuthor |
P129784
|
FINISHED |
| Object | J. R. R. Tolkien |
—
|
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: J. R. R. Tolkien | Statement: [The Treason of Isengard, mainSubjectAuthor, J. R. R. Tolkien]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainSubjectAuthor Context triple: [The Treason of Isengard, mainSubjectAuthor, J. R. R. Tolkien]
-
A.
authorRelationshipToMainSubject
Indicates the nature of the connection or role the author has in relation to the main subject.
-
B.
publisherOfWorkAboutSubject
Indicates that an entity is the publisher of a work whose content is about a specified subject.
-
C.
authorType
Indicates the specific role or category of authorship associated with an entity, such as primary author, co-author, or editor.
-
D.
subjectOfWorkBy
chosen
Indicates that one entity is the main topic or focus of a work (such as a book, article, or artwork) created by another entity.
-
E.
hasAuthorRelationshipToSubject
Indicates that an entity serves as the author or creator of the specified 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_69f76e93ec4c8190be81cf87354d9155 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.