Triple

T11564323
Position Surface form Disambiguated ID Type / Status
Subject Shivta E274215 entity
Predicate tradingRoute P35626 FINISHED
Object incense trade route 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: incense trade route | Statement: [Shivta, tradingRoute, incense trade route]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: tradingRoute
Context triple: [Shivta, tradingRoute, incense trade route]
  • A. includesTradeRoute chosen
    Indicates that one entity contains, encompasses, or makes use of a particular trade route within its scope or structure.
  • B. tradRoutes
    Indicates a relationship where one location serves as a trade route to or from another location, facilitating the movement of goods or commerce between them.
  • C. tradingApproach
    Indicates the method or strategy an entity uses to conduct trading activities or make trade-related decisions.
  • D. tradingSegment
    Indicates that one entity operates within, or is associated with, a specific trading segment or market subdivision for transactional activities.
  • E. tradingLinks
    Indicates that there are established trade or commercial exchange relationships between the referenced entities.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88dd321f88190a57ecaf079fbbc3f completed April 10, 2026, 5:42 a.m.
PD Predicate disambiguation batch_69d85dc3fc2c8190bed7e2111301a77c completed April 10, 2026, 2:17 a.m.
Created at: April 8, 2026, 9:37 p.m.