Triple
T21526191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linda Lingle |
E531102
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Linda Lingle |
—
|
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: Linda Lingle | Statement: [Linda Lingle, name, Linda Lingle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Linda Lingle Context triple: [Linda Lingle, name, Linda Lingle]
-
A.
Linda Lingle
chosen
Linda Lingle is an American politician who served as the sixth governor of Hawaii and the state's first female and first Jewish governor.
-
B.
Mary Kagi
Mary Kagi was the mother of abolitionist John Henry Kagi, who was a key lieutenant of John Brown during the lead-up to the American Civil War.
-
C.
David Ige
David Ige is an American politician who served as the governor of Hawaii from 2014 to 2022.
-
D.
Lou Leon Guerrero
Lou Leon Guerrero is an American politician and former nurse who became the first female governor of Guam.
-
E.
Lindsay Dole
Lindsay Dole is a driven and morally conflicted defense attorney on the legal drama series "The Practice," known for her complex personal and professional relationships within the firm.
- 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee88515874819085e251c0d297a587 |
completed | April 26, 2026, 9:49 p.m. |
Created at: April 16, 2026, 6:26 p.m.