Triple

T21137138
Position Surface form Disambiguated ID Type / Status
Subject Kroraina E520841 entity
Predicate connectedRoutes P130931 FINISHED
Object southern Silk Road route around Taklamakan Desert LITERAL 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: southern Silk Road route around Taklamakan Desert | Statement: [Kroraina, connectedRoutes, southern Silk Road route around Taklamakan Desert]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: connectedRoutes
Context triple: [Kroraina, connectedRoutes, southern Silk Road route around Taklamakan Desert]
  • A. usedRoutes
    Indicates that an entity has utilized or traveled along specific routes.
  • B. routesFrom
    Indicates that something (such as a path, connection, or communication) originates at one entity and is directed or carried from that source entity toward another.
  • C. parallelRoute
    Indicates that one route runs alongside and in the same general direction as another route without intersecting it.
  • D. isRelatedRouteOf chosen
    Indicates that one route is connected to, associated with, or serves as an alternative or complementary path to another route.
  • E. firstRoutes
    Indicates that one route or path is the initial or primary route taken or assigned among a set of possible routes.
  • F. None of above.

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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7235b89188190a6209c0a1839ee03 completed April 21, 2026, 7:12 a.m.
PD Predicate disambiguation batch_69e5f5ed6c8c8190b31092a5d4c3de5d completed April 20, 2026, 9:46 a.m.
Created at: April 16, 2026, 2:57 p.m.