Triple
T19509742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louise Erdrich |
E488114
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Pallas 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: Pallas Erdrich | Statement: [Louise Erdrich, hasChild, Pallas Erdrich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pallas Erdrich Context triple: [Louise Erdrich, hasChild, Pallas Erdrich]
-
A.
Pallas Erdrich
chosen
Pallas Erdrich is a daughter of acclaimed Native American author Louise Erdrich.
-
B.
Aza Erdrich
Aza Erdrich is one of the daughters of acclaimed Native American author Louise Erdrich.
-
C.
Louise Erdrich
Louise Erdrich is an acclaimed American author known for her richly layered novels about Native American life, identity, and history, including works such as "Love Medicine" and "The Round House."
-
D.
Linda Hogan
Linda Hogan is a Chickasaw poet, novelist, and environmentalist whose work powerfully explores Native American identity, history, and relationships with the natural world.
-
E.
Linda Hogan
Linda Hogan is an American television personality and the ex-wife of professional wrestler Hulk Hogan, best known for appearing on the reality series "Hogan Knows Best."
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6351547e481909a875bba40651094 |
completed | April 20, 2026, 2:15 p.m. |
Created at: April 10, 2026, 1:40 p.m.