Triple
T21787466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbert Hoover |
E537876
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Herbert Hoover Jr. |
—
|
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: Herbert Hoover Jr. | Statement: [Herbert Hoover, child, Herbert Hoover Jr.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herbert Hoover Jr. Context triple: [Herbert Hoover, child, Herbert Hoover Jr.]
-
A.
Herbert Hoover Jr.
chosen
Herbert Hoover Jr. was an American engineer, businessman, and diplomat who served as U.S. Under Secretary of State during the Eisenhower administration.
-
B.
Thomas Hoover
Thomas Hoover is an American novelist best known for his historical fiction works, including the epic novel "The Moghul."
-
C.
Slim Hoover
Slim Hoover is a fictional character appearing in the 1920 silent Western film "The Round-Up."
-
D.
Christopher du Pont Roosevelt
Christopher du Pont Roosevelt was an American businessman and member of both the Roosevelt presidential family and the wealthy du Pont industrial family.
-
E.
Robert Barnhill Roosevelt
Robert Barnhill Roosevelt was an American politician, diplomat, and conservationist, and the uncle of President Theodore Roosevelt.
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0621c68588190977891055e80a499 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 16, 2026, 6:52 p.m.