Triple

T36147653

Position	Surface form	Disambiguated ID	Type / Status
Subject	Kosaraju's algorithm	`E1045495`	entity
Predicate	usesTraversal	`P192604`	FINISHED
Object	depth-first search Depth-first search is a graph traversal algorithm that explores as far as possible along each branch before backtracking, commonly used as a building block in many graph algorithms.	`E2171558`	NE FINISHED

How this triple was built (3 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: depth-first search | Statement: [Kosaraju's algorithm, usesTraversal, depth-first search]

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: depth-first search
Triple: [Kosaraju's algorithm, usesTraversal, depth-first search]

Generated description

Depth-first search is a graph traversal algorithm that explores as far as possible along each branch before backtracking, commonly used as a building block in many graph algorithms.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: usesTraversal
Context triple: [Kosaraju's algorithm, usesTraversal, depth-first search]

A. formerTraversal
Indicates that one entity previously traversed, passed through, or traveled along another entity, but is no longer doing so.
B. alsoTraverses
Indicates that a route, path, or entity passes through or crosses an additional location or segment beyond its primary traversal.
C. requiresTraversalDirection
Indicates that a relationship or process can only be correctly followed or applied when moving through a structure in a specified direction.
D. enablesTraversal
Indicates that one entity provides the means or capability for another entity to move through, across, or along something.
E. launcherTraverse
Indicates the movement or rotation of a launcher mechanism as it traverses across its operational arc or axis.
F. None of above. chosen

Provenance (7 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_69f76e37ace88190a906b107d388f5d1`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69fd19f791f48190bbb6f6047f9ddc59`	completed	May 7, 2026, 11:02 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a390d4acba88190aed90daed14a0f75`	completed	June 22, 2026, 10:24 a.m.
NEDg	Description generation	`batch_6a390dedf15c819089930dbade349fbc`	completed	June 22, 2026, 10:26 a.m.
NED2	Entity disambiguation (via description)	`batch_6a390f02997881909c5588ca5ad3426a`	completed	June 22, 2026, 10:31 a.m.
PD	Predicate disambiguation	`batch_69fd0df365948190bc9bfc7ffd46acd8`	completed	May 7, 2026, 10:10 p.m.
PDg	Predicate description generation	`batch_69fd19f6a7888190aa7eee2b87687c53`	completed	May 7, 2026, 11:02 p.m.

Created at: May 3, 2026, 4:08 p.m.