Triple

T21267520
Position Surface form Disambiguated ID Type / Status
Subject Hanya Holm E524165 entity
Predicate notableWork P4 FINISHED
Object The City
"The City" is a modern dance work choreographed by influential German-American dancer and teacher Hanya Holm.
E1475921 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: The City | Statement: [Hanya Holm, notableWork, The City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The City
Context triple: [Hanya Holm, notableWork, The City]
  • A. The City
    The City is a 1919–1920 Cubist painting by Fernand Léger that depicts the dynamism and fragmentation of modern urban life through bold colors and geometric forms.
  • B. The City
    The City is the nickname of Brechin City F.C., a Scottish football club based in Brechin, Angus.
  • C. The City
    The City is the common nickname for King’s Landing, the bustling and politically charged capital of the Seven Kingdoms in the world of Game of Thrones.
  • D. The City
    "The City" is a hip-hop track by Game featuring Kendrick Lamar, known for its gritty portrayal of urban life and standout lyrical performances.
  • E. The City
    The City is a sprawling, dystopian futuristic metropolis that serves as the chaotic, cyberpunk-style backdrop for Warren Ellis and Darick Robertson’s comic series Transmetropolitan.
  • 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: The City
Triple: [Hanya Holm, notableWork, The City]
Generated description
"The City" is a modern dance work choreographed by influential German-American dancer and teacher Hanya Holm.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: The City
Target entity description: "The City" is a modern dance work choreographed by influential German-American dancer and teacher Hanya Holm.
  • A. The City
    The City is a 1919–1920 Cubist painting by Fernand Léger that depicts the dynamism and fragmentation of modern urban life through bold colors and geometric forms.
  • B. The City
    The City is a landmark 1939 American documentary film, co-directed by Ralph Steiner and Willard Van Dyke with contributions from Alexander Hammid, that critiques industrial urban life and advocates for planned communities.
  • C. The City
    The City is a work associated with Laura Wright, likely a creative piece such as a novel, play, or other artistic production.
  • D. The City
    "The City" is an atmospheric, synthesizer-driven track by Vangelis that showcases his signature cinematic and electronic sound.
  • E. The City
    "The City" is a poem by James Henry published in his collection *Valeria and Other Poems*, reflecting his characteristic introspective and reflective poetic style.
  • 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_69e0b5156d7881909bd4f83676590715 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e735ee38cc81909b4e7c5996bb64f9 completed April 21, 2026, 8:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0997fc8dfc819097d34d1833b95fa0 completed May 17, 2026, 10:27 a.m.
NEDg Description generation batch_6a09991ba4d88190adc8a0baaeb06b8f completed May 17, 2026, 10:31 a.m.
NED2 Entity disambiguation (via description) batch_6a0999a97a2081908c20cd6db9f7a15a completed May 17, 2026, 10:34 a.m.
Created at: April 16, 2026, 4 p.m.