Triple
T22703749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joni Ernst |
E561389
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object | Tom Harkin |
—
|
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: Tom Harkin | Statement: [Joni Ernst, precededBy, Tom Harkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Harkin Context triple: [Joni Ernst, precededBy, Tom Harkin]
-
A.
Tom Harkin
chosen
Tom Harkin is an American Democratic politician and longtime U.S. senator from Iowa known for his leadership on disability rights and authorship of the Americans with Disabilities Act.
-
B.
Theo Dorgan
Theo Dorgan is an Irish poet, writer, and broadcaster known for his lyrical verse, literary advocacy, and contributions to contemporary Irish literature.
-
C.
Ben Nelson
Ben Nelson is an American politician who served as the Democratic U.S. Senator from Nebraska from 2001 to 2013 and previously as the state's governor.
-
D.
Carl Levin
Carl Levin was a long-serving U.S. Senator from Michigan known for his leadership on national security and defense oversight, including as chair of the Senate Armed Services Committee.
-
E.
Carl Levin
Carl Levin is a film producer best known for his work on the musical comedy movie "Rock of Ages."
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cca1e48190bbe7910f13692803 |
completed | April 29, 2026, 3:19 a.m. |
Created at: April 17, 2026, 3:16 p.m.