Triple

T26711511
Position Surface form Disambiguated ID Type / Status
Subject Reisterstown, Maryland E673424 entity
Predicate mainHistoricThoroughfare P17497 FINISHED
Object Main Street
Main Street is the central historic thoroughfare and primary commercial corridor in Reisterstown, Maryland, known for its preserved architecture and local businesses.
 E2204449 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: Main Street | Statement: [Reisterstown, Maryland, mainHistoricThoroughfare, Main Street]
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: Main Street
Triple: [Reisterstown, Maryland, mainHistoricThoroughfare, Main Street]
Generated description
Main Street is the central historic thoroughfare and primary commercial corridor in Reisterstown, Maryland, known for its preserved architecture and local businesses.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: mainHistoricThoroughfare
Context triple: [Reisterstown, Maryland, mainHistoricThoroughfare, Main Street]
  • A. hasHistoricStreet chosen
    Indicates that an entity is associated with or located on a street that has recognized historical significance.
  • B. avenueRadiatingFrom
    Indicates that one avenue extends outward from and is oriented away from another central point or thoroughfare, like a spoke radiating from a hub.
  • C. roadName
    Indicates the specific name assigned to a road that identifies it within a transportation or address system.
  • D. isNumberedAvenueOf
    Indicates that one entity is an avenue identified by a numerical designation that belongs to or is part of the other entity (such as a city or road network).
  • E. hasHeadquartersOnStreet
    Indicates that an organization’s headquarters is located on a specific street.
  • F. None of above.

Provenance (6 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_69eecda3a22881908f3061c760b9d542 completed April 27, 2026, 2:44 a.m.
NER Named-entity recognition batch_69f617bf61dc8190916187025854e15c completed May 2, 2026, 3:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3e1600f2bc8190a89ea4960bf9dcba completed June 26, 2026, 6:02 a.m.
NEDg Description generation batch_6a3e17efad28819094f9722d0e032fbd completed June 26, 2026, 6:10 a.m.
NED2 Entity disambiguation (via description) batch_6a3e1ce7fda88190abe048342ab44b3a completed June 26, 2026, 6:32 a.m.
PD Predicate disambiguation batch_69f60b8dfa0c8190864e1a940024d0a0 completed May 2, 2026, 2:34 p.m.
Created at: April 27, 2026, 3:35 a.m.