Triple
T21958573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oscar Hubbard |
E542259
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Leo Hubbard |
—
|
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: Leo Hubbard | Statement: [Oscar Hubbard, relative, Leo Hubbard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Hubbard Context triple: [Oscar Hubbard, relative, Leo Hubbard]
-
A.
Leo Hubbard
chosen
Leo Hubbard is a central character in Lillian Hellman’s play “The Little Foxes,” known as one of the scheming, ambitious members of the Hubbard family.
-
B.
George Bagby
George Bagby was the crime and mystery fiction pseudonym of American author Aaron Marc Stein, under which he wrote a popular series of detective novels.
-
C.
Alanson Shearer
Alanson Shearer was an early local figure of significance in Michigan, likely a pioneer settler or landowner, after whom the village of Alanson, Michigan, was named.
-
D.
Frank Irving Cobb
Frank Irving Cobb was an influential American journalist and editor best known for leading the New York World’s editorial page in the early 20th century.
-
E.
Eaton L. Dickey
Eaton L. Dickey was an American diplomat who served as a U.S. ambassador, notably representing the United States in Panama.
- 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1244204f081909742d4fe138610d6 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 8 p.m.