Triple
T21755838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Lloyd Praeger |
E537036
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Praeger |
—
|
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: Praeger | Statement: [Robert Lloyd Praeger, familyName, Praeger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Praeger Context triple: [Robert Lloyd Praeger, familyName, Praeger]
-
A.
Praeger
chosen
Praeger is a surname of Irish origin borne by various notable individuals and families.
-
B.
Praeger
Praeger is an American academic and professional publishing company known for its books in the social sciences, humanities, and public policy.
-
C.
M. E. Sharpe
M. E. Sharpe is an academic publishing company known for its scholarly books and journals in the social sciences and humanities.
-
D.
Westview Press
Westview Press is an academic publishing imprint known for producing scholarly and educational books, particularly in the social sciences and humanities.
-
E.
University Press of America
University Press of America is an academic publishing imprint known for producing scholarly and educational books across a wide range of disciplines.
- 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_69e0c46eab808190b848242d63a17c47 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01d8ea04c8190a8c4fa43b3f23935 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 16, 2026, 6:50 p.m.