Triple

T15918699
Position Surface form Disambiguated ID Type / Status
Subject John B. Kruskal E386036 entity
Predicate notableWork P4 FINISHED
Object Kruskal's algorithm for minimum spanning trees E1045593 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: Kruskal's algorithm for minimum spanning trees | Statement: [John B. Kruskal, notableWork, Kruskal's algorithm for minimum spanning trees]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kruskal's algorithm for minimum spanning trees
Context triple: [John B. Kruskal, notableWork, Kruskal's algorithm for minimum spanning trees]
  • A. Kruskal’s minimum spanning tree algorithm chosen
    Kruskal’s minimum spanning tree algorithm is a classic greedy graph algorithm that builds a minimum spanning tree by repeatedly adding the smallest-weight edge that does not create a cycle, typically implemented efficiently using a union–find data structure.
  • B. Prim's minimum spanning tree algorithm
    Prim's minimum spanning tree algorithm is a greedy graph algorithm that incrementally builds a minimum-cost spanning tree by repeatedly adding the cheapest edge connecting the growing tree to a new vertex.
  • C. Kruskal
    Kruskal is a surname most prominently associated with American mathematician Martin David Kruskal, known for his work in soliton theory and nonlinear science.
  • D. Cristian's algorithm
    Cristian's algorithm is a clock synchronization method in distributed systems that estimates accurate time on client machines by querying a time server and adjusting for message delays.
  • E. Lipton–Tarjan separator theorem
    The Lipton–Tarjan separator theorem is a fundamental result in graph theory that shows any planar graph can be efficiently divided into roughly equal parts by removing only a relatively small set of vertices, enabling faster algorithms for many computational problems.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1567ff9e48190b73cb101fc3f7b2b completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb05d1fb481909b42bea774a15c70 completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:52 a.m.