Triple

T12277749
Position Surface form Disambiguated ID Type / Status
Subject Margery Sharp E292633 entity
Predicate wrote P2831 FINISHED
Object Something Light
Something Light is a mid-20th-century comic novel by British author Margery Sharp, known for its witty portrayal of an independent young woman navigating work and romance in London.
 E976208 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: Something Light | Statement: [Margery Sharp, wrote, Something Light]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Something Light
Context triple: [Margery Sharp, wrote, Something Light]
  • A. Simply Light
    Simply Light is a reduced-calorie line of fruit juices and beverages offered under the Simply brand.
  • B. More Light
    More Light is a 2013 studio album by Scottish rock band Primal Scream that blends alternative rock, psychedelia, and experimental sounds.
  • C. One Light
    "One Light" is a song by Dutch electronic music producer and DJ Jordi.
  • D. Just a Little Light
    "Just a Little Light" is a song by the Grateful Dead, featured on their 1989 studio album "Built to Last."
  • E. Different Light
    Different Light is the 1986 pop-rock album by the Bangles that brought them mainstream success with hits like "Manic Monday" and "Walk Like an Egyptian."
  • 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: Something Light
Triple: [Margery Sharp, wrote, Something Light]
Generated description
Something Light is a mid-20th-century comic novel by British author Margery Sharp, known for its witty portrayal of an independent young woman navigating work and romance in London.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Something Light
Target entity description: Something Light is a mid-20th-century comic novel by British author Margery Sharp, known for its witty portrayal of an independent young woman navigating work and romance in London.
  • A. Simply Light
    Simply Light is a reduced-calorie line of fruit juices and beverages offered under the Simply brand.
  • B. More Light
    More Light is a 2013 studio album by Scottish rock band Primal Scream that blends alternative rock, psychedelia, and experimental sounds.
  • C. One Light
    "One Light" is a song by Dutch electronic music producer and DJ Jordi.
  • D. Just a Little Light
    "Just a Little Light" is a song by the Grateful Dead, featured on their 1989 studio album "Built to Last."
  • E. Different Light
    Different Light is the 1986 pop-rock album by the Bangles that brought them mainstream success with hits like "Manic Monday" and "Walk Like an Egyptian."
  • 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_69d6ab6856488190b5d31178d5015f8e completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cf06cf08190ac8671dd9bbed03d completed April 10, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e6d72d081908c8697257df712f1 completed May 2, 2026, 3:55 p.m.
NEDg Description generation batch_69f620759f348190baa9af5b33d4e37f completed May 2, 2026, 4:04 p.m.
NED2 Entity disambiguation (via description) batch_69f624bf23948190b182e4c31564d210 completed May 2, 2026, 4:22 p.m.
Created at: April 8, 2026, 9:52 p.m.