Triple
T24220716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | White Earth Ojibwe |
E601447
|
entity |
| Predicate | hasNotableWriterFrom |
P10455
|
FINISHED |
| Object | Louise Erdrich |
—
|
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: Louise Erdrich | Statement: [White Earth Ojibwe, hasNotableWriterFrom, Louise Erdrich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableWriterFrom Context triple: [White Earth Ojibwe, hasNotableWriterFrom, Louise Erdrich]
-
A.
hasNotableWriter
chosen
Indicates that an entity is associated with a writer who is recognized as significant or distinguished in some notable way.
-
B.
hasNotableAuthorWork
Indicates that an author is notably associated with creating a particular work.
-
C.
notableAuthorMember
Indicates that an entity is a notable or distinguished author who is a member of a particular group, organization, or collection.
-
D.
notableAuthorPublished
Indicates that a work was published by an author who is recognized as notable or distinguished.
-
E.
notWrittenBy
Indicates that a specified work or content is explicitly not authored or created by a given entity.
- 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_69e29537ca548190b94a37ebe1977caf |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f2820cdd3c8190998d6d901224c09f |
completed | April 29, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:59 p.m.