Triple

T16357042
Position Surface form Disambiguated ID Type / Status
Subject Here Be Dragons E397207 entity
Predicate notableWork P4 FINISHED
Object Walking New York
Walking New York is a short documentary film that follows French artist JR as he creates a large-scale public art installation on the streets of New York City.
 E1207947 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: Walking New York | Statement: [Here Be Dragons, notableWork, Walking New York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Walking New York
Context triple: [Here Be Dragons, notableWork, Walking New York]
  • A. Sidewalks of New York
    Sidewalks of New York is a 2001 romantic comedy-drama film written, directed by, and starring Edward Burns that interweaves the love lives of several New Yorkers.
  • B. The Streets of New York
    "The Streets of New York" is a song by Irish musician Brian Warfield, best known as a ballad vividly depicting life and experiences in New York City.
  • C. A Map of New York
    "A Map of New York" is a song by the indie rock band If/Then.
  • D. New York Scenes
    New York Scenes is a section of Jack Kerouac’s travelogue "Lonesome Traveler" that captures his impressions and experiences of life in New York City.
  • E. NYC Life
    NYC Life is a New York City-based television channel that focuses on local culture, lifestyle, and city-centric programming.
  • 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: Walking New York
Triple: [Here Be Dragons, notableWork, Walking New York]
Generated description
Walking New York is a short documentary film that follows French artist JR as he creates a large-scale public art installation on the streets of New York City.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Walking New York
Target entity description: Walking New York is a short documentary film that follows French artist JR as he creates a large-scale public art installation on the streets of New York City.
  • A. Sidewalks of New York
    Sidewalks of New York is a 2001 romantic comedy-drama film written, directed by, and starring Edward Burns that interweaves the love lives of several New Yorkers.
  • B. The Streets of New York
    "The Streets of New York" is a song by Irish musician Brian Warfield, best known as a ballad vividly depicting life and experiences in New York City.
  • C. A Map of New York
    "A Map of New York" is a song by the indie rock band If/Then.
  • D. New York Scenes
    New York Scenes is a section of Jack Kerouac’s travelogue "Lonesome Traveler" that captures his impressions and experiences of life in New York City.
  • E. NYC Life
    NYC Life is a New York City-based television channel that focuses on local culture, lifestyle, and city-centric programming.
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2facf67e0819089a23ce6f5642fbe completed April 18, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002dbaacd88190b2c90c5be2832307 completed May 10, 2026, 7:03 a.m.
NEDg Description generation batch_6a002e92e840819080219d51dd6ddb34 completed May 10, 2026, 7:06 a.m.
NED2 Entity disambiguation (via description) batch_6a002f171b588190b4690a28657fa76e completed May 10, 2026, 7:09 a.m.
Created at: April 10, 2026, 5:07 a.m.