Triple

T144653
Position Surface form Disambiguated ID Type / Status
Subject Magnificent Mile E2927 entity
Predicate streetSectionOf P5397 FINISHED
Object Michigan Avenue E32738 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: Michigan Avenue | Statement: [Magnificent Mile, streetSectionOf, Michigan Avenue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michigan Avenue
Context triple: [Magnificent Mile, streetSectionOf, Michigan Avenue]
  • A. South Michigan Avenue
    South Michigan Avenue is a major thoroughfare in downtown Chicago known for its cultural landmarks, historic architecture, and proximity to Grant Park.
  • B. North Michigan Avenue chosen
    North Michigan Avenue is a major commercial thoroughfare in Chicago renowned for its upscale shopping, dining, and landmark architecture.
  • C. Franklin Avenue
    Franklin Avenue is a notable east–west thoroughfare in Los Angeles, California, running through the Hollywood area and known for its historic residential neighborhoods and proximity to major Hollywood landmarks.
  • D. Main Street
    Main Street is a major thoroughfare in downtown Dallas, Texas, running through historic areas including Dealey Plaza.
  • E. State Street and Washington Avenue
    State Street and Washington Avenue is a major intersection in downtown Albany, New York, located directly in front of the New York State Capitol building.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: streetSectionOf
Context triple: [Magnificent Mile, streetSectionOf, Michigan Avenue]
  • A. hasStreet
    Indicates that an entity is located on, associated with, or identified by a particular street.
  • B. roadFeature
    Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
  • C. streetNetwork
    Indicates the layout and connectivity relationships among streets within a geographic area, including how roads intersect, link, and form a navigable network.
  • D. roadType
    Indicates the classification or category of a road based on its functional or physical characteristics.
  • E. roadSystem
    Indicates a relationship where multiple roads are organized and connected as part of a larger, integrated transportation network or infrastructure.
  • F. None of above. chosen

Provenance (5 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257e935bc8190a03e54a10e9ba6f7 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3795173e88190afe87259edd4f275 completed Feb. 28, 2026, 11:25 p.m.
PD Predicate disambiguation batch_69a25656a4fc81908a87678ac3d28f93 completed Feb. 28, 2026, 2:43 a.m.
PDg Predicate description generation batch_69a257101060819094db0f3a3a72f312 completed Feb. 28, 2026, 2:46 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.