Triple

T17353996
Position Surface form Disambiguated ID Type / Status
Subject Walter Kerr E421886 entity
Predicate placeOfActivity P1527 FINISHED
Object Broadway
Broadway is New York City's famed theater district and the historic center of American commercial stage productions.
E16252 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: Broadway | Statement: [Walter Kerr, placeOfActivity, Broadway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Broadway
Context triple: [Walter Kerr, placeOfActivity, Broadway]
  • A. Broadway
    Broadway is a major thoroughfare in Oakland, California, serving as a key commercial and transportation corridor through the city’s downtown.
  • B. Broadway
    Broadway is a major east–west thoroughfare in Vancouver, British Columbia, known as one of the city’s primary commercial and transit corridors.
  • C. Broadway
    Broadway is a major north–south thoroughfare on Chicago’s North Side known for its dense mix of shops, restaurants, and neighborhood commercial districts.
  • D. Broadway
    Broadway is a major thoroughfare that runs through the hamlet of Massapequa in Nassau County, New York.
  • E. Broadway
    Broadway is a major east–west thoroughfare in Monmouth County, New Jersey, serving as a locally known segment of County Route 537.
  • 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: Broadway
Triple: [Walter Kerr, placeOfActivity, Broadway]
Generated description
Broadway is New York City's famed theater district and the historic center of American commercial stage productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Broadway
Target entity description: Broadway is New York City's famed theater district and the historic center of American commercial stage productions.
  • A. Broadway chosen
    Broadway is a major thoroughfare in New York City famous for its historic theaters and role as the heart of American commercial theater.
  • B. Broadway
    Broadway is a style of American musical theater characterized by its theatrical song-and-dance numbers, dramatic storytelling, and association with New York City's major commercial stage productions.
  • C. Broadway
    Broadway is a historic thoroughfare in downtown Los Angeles known for its early 20th-century theaters and vibrant commercial activity.
  • D. Broadway
    Broadway is the main thoroughfare and historic commercial street running through the city of Kingston, New York.
  • E. Broadway
    Broadway is a major north–south thoroughfare on Chicago’s North Side known for its dense mix of shops, restaurants, and neighborhood commercial districts.
  • F. None of above.

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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a2e660c81908700aed5c42e9043 completed April 19, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01afe164d48190aa3d4eefe0ef12a3 completed May 11, 2026, 10:30 a.m.
NEDg Description generation batch_6a01b1151a488190ad4523c48f9e305c completed May 11, 2026, 10:36 a.m.
NED2 Entity disambiguation (via description) batch_6a01b18771f481908fb98fce28d7a72e completed May 11, 2026, 10:37 a.m.
Created at: April 10, 2026, 5:44 a.m.