Triple

T70648
Position Surface form Disambiguated ID Type / Status
Subject SF E1413 entity
Predicate context P36 FINISHED
Object US postal system E2555 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: US postal system | Statement: [SF, context, US postal system]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: US postal system
Context triple: [SF, context, US postal system]
  • A. United States Postal Service chosen
    The United States Postal Service is an independent agency of the U.S. federal government responsible for providing nationwide postal delivery and related mail services.
  • B. Universal Postal Union
    The Universal Postal Union is a specialized United Nations agency that coordinates international postal policies and services among member countries to ensure a unified global mail system.
  • C. FedEx
    FedEx is a global courier delivery services company known for its overnight shipping and pioneering real-time package tracking.
  • D. FedExField
    FedExField is a large outdoor football stadium in Landover, Maryland, best known as the longtime home venue of Washington’s NFL franchise.
  • E. Amtrak
    Amtrak is the United States’ national passenger railroad service, operating intercity and long-distance trains across much of the country.
  • 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_69a24c06b3bc8190aa4ac89026115efc completed Feb. 28, 2026, 1:59 a.m.
NER Named-entity recognition batch_69a24f0578808190be793d7a161c2cf5 completed Feb. 28, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69a26241d4c08190885dab6aef75dcf3 completed Feb. 28, 2026, 3:34 a.m.
Created at: Feb. 28, 2026, 2:03 a.m.