Triple

T5618261
Position Surface form Disambiguated ID Type / Status
Subject Irish Channel E147531 entity
Predicate hasStreet P959 FINISHED
Object Constance Street
Constance Street is a residential and commercial street located in the historic Irish Channel neighborhood of New Orleans, Louisiana.
 E897874 NE FINISHED

How this triple was built (4 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: Constance Street | Statement: [Irish Channel, hasStreet, Constance Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Constance Street
Context triple: [Irish Channel, hasStreet, Constance Street]
  • A. Warren Street
    Warren Street is a major thoroughfare in Boston, Massachusetts, that functions as an important transit corridor and local commercial-residential street.
  • B. Warren Street
    Warren Street is the historic main commercial thoroughfare in Hudson, New York, known for its shops, galleries, and restaurants.
  • C. Warren Street
    Warren Street is a London Underground station in central London served by the Northern and Victoria lines.
  • D. Hurst Street
    Hurst Street is a well-known street in Birmingham, England, recognized for its nightlife and as the heart of the city’s Gay Village.
  • E. Wellesley Street
    Wellesley Street is a major east–west thoroughfare in downtown Toronto, Ontario, running through the city’s core near key civic and institutional landmarks.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Constance Street
Triple: [Irish Channel, hasStreet, Constance Street]
Generated description
Constance Street is a residential and commercial street located in the historic Irish Channel neighborhood of New Orleans, Louisiana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Constance Street
Target entity description: Constance Street is a residential and commercial street located in the historic Irish Channel neighborhood of New Orleans, Louisiana.
  • A. Warren Street
    Warren Street is a major thoroughfare in Boston, Massachusetts, that functions as an important transit corridor and local commercial-residential street.
  • B. Warren Street
    Warren Street is the historic main commercial thoroughfare in Hudson, New York, known for its shops, galleries, and restaurants.
  • C. Warren Street
    Warren Street is a London Underground station in central London served by the Northern and Victoria lines.
  • D. Hurst Street
    Hurst Street is a well-known street in Birmingham, England, recognized for its nightlife and as the heart of the city’s Gay Village.
  • E. Wellesley Street
    Wellesley Street is a major east–west thoroughfare in downtown Toronto, Ontario, running through the city’s core near key civic and institutional landmarks.
  • 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_69c00905d4588190bd967842bbcf2219 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c021dd5d0081909d18d16596fac507 completed March 22, 2026, 5:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69e343941ae481909489cf7a4abdba68 completed April 18, 2026, 8:40 a.m.
NEDg Description generation batch_69e3556ad7ec819095b3babc67ecdfd4 completed April 18, 2026, 9:56 a.m.
NED2 Entity disambiguation (via description) batch_69e358f860f08190bfd10519ff3806aa completed April 18, 2026, 10:12 a.m.
Created at: March 22, 2026, 3:40 p.m.