Triple
T16983573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alan Hoffman |
E412003
|
entity |
| Predicate | coAuthor |
P398
|
FINISHED |
| Object | J. B. Kruskal |
E1190567
|
NE FINISHED |
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: J. B. Kruskal | Statement: [Alan Hoffman, coAuthor, J. B. Kruskal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: J. B. Kruskal Context triple: [Alan Hoffman, coAuthor, J. B. Kruskal]
-
A.
William Kruskal
William Kruskal was an American statistician best known for co-developing the Kruskal–Wallis test, a nonparametric method for comparing multiple groups.
-
B.
John Kruskal
John Kruskal was an American mathematician and computer scientist best known for Kruskal's algorithm in graph theory and for foundational work in combinatorics and statistics.
-
C.
Joseph B. Kruskal
chosen
Joseph B. Kruskal was an American mathematician and statistician known for Kruskal's algorithm in graph theory, multidimensional scaling, and contributions to nonparametric statistics.
-
D.
Joseph Kruskal Sr.
Joseph Kruskal Sr. was the father of mathematician John B. Kruskal and a member of the prominent Kruskal family known for its contributions to mathematics and science.
-
E.
Jack Edmonds
Jack Edmonds is a pioneering Canadian mathematician and computer scientist renowned for his foundational work in combinatorial optimization and polyhedral theory, including the development of efficient algorithms for matching and matroid intersection.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d188ede48190baead48aac84c78d |
completed | April 18, 2026, 6:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc0f13c88190b55da5be40a0a476 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:32 a.m.