Triple

T9511328
Position Surface form Disambiguated ID Type / Status
Subject Cecil Kellaway E229402 entity
Predicate notableWork P4 FINISHED
Object Harvey
"Harvey" is a classic 1950 American comedy film, based on Mary Chase's play, about a genial man whose best friend is an invisible six-foot-tall rabbit.
 E151799 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: Harvey | Statement: [Cecil Kellaway, notableWork, Harvey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harvey
Context triple: [Cecil Kellaway, notableWork, Harvey]
  • A. Harvey
    Harvey is the middle name of Lee Harvey Oswald, the alleged assassin of U.S. President John F. Kennedy.
  • B. Harvey
    Harvey is a rural town in the South West of Western Australia known for its agriculture, dairy production, and citrus orchards.
  • C. Harvey
    Harvey is a masculine given name of Old English origin meaning "battle worthy" or "strong in battle."
  • D. Harvey
    Harvey is a character from the Broadway musical "Hallelujah, Baby!", which explores themes of race, ambition, and social change in 20th-century America.
  • E. Harvey
    Harvey is a botanist and taxonomist known for formally describing the plant genus Romneya.
  • 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: Harvey
Triple: [Cecil Kellaway, notableWork, Harvey]
Generated description
"Harvey" is a classic 1950 American comedy film, based on Mary Chase's play, about a genial man whose best friend is an invisible six-foot-tall rabbit.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harvey
Target entity description: "Harvey" is a classic 1950 American comedy film, based on Mary Chase's play, about a genial man whose best friend is an invisible six-foot-tall rabbit.
  • A. Harvey chosen
    Harvey is a classic 1950 American comedy film in which James Stewart plays a genial man whose best friend is an invisible six-foot-tall rabbit.
  • B. Harvey
    Harvey is a character from the Broadway musical "Hallelujah, Baby!", which explores themes of race, ambition, and social change in 20th-century America.
  • C. Harvey
    Harvey is the middle name of Lee Harvey Oswald, the alleged assassin of U.S. President John F. Kennedy.
  • D. Harvey
    Harvey is a rural town in the South West of Western Australia known for its agriculture, dairy production, and citrus orchards.
  • E. Harvey
    Harvey is a botanist and taxonomist known for formally describing the plant genus Romneya.
  • 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_69ca84777560819084cddd999badc1aa completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9868616c8190856f89fecfa1a02e completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1526d30a481909944110fd6ebd1dd completed April 4, 2026, 6:03 p.m.
NEDg Description generation batch_69d1543fc8e88190922196c5a462fb3e completed April 4, 2026, 6:11 p.m.
NED2 Entity disambiguation (via description) batch_69d15494c0b88190bef5901bce98e283 completed April 4, 2026, 6:12 p.m.
Created at: March 30, 2026, 7:58 p.m.