Triple

T8799832
Position Surface form Disambiguated ID Type / Status
Subject London Marathon E209376 entity
Predicate formerSponsor P18226 FINISHED
Object Flora
Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
 E759860 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: Flora | Statement: [London Marathon, formerSponsor, Flora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Flora
Context triple: [London Marathon, formerSponsor, Flora]
  • A. Flora
    Flora is a celebrated 19th-century botanical illustration by Mary Evelyn Pickering that showcases her detailed and artistic rendering of plant life.
  • B. Flora
    Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
  • C. Flora
    Flora is the young niece in Henry James's novella "The Turn of the Screw," whose eerie innocence and ambiguous relationship to the supernatural are central to the story's psychological horror.
  • D. Flora
    Flora is the middle name of Ruth Disney, the daughter of Walt Disney and his wife Lillian.
  • E. Flora
    Flora is one of the three good fairies in Disney's "Sleeping Beauty," known for her red attire, leadership among the fairies, and role in protecting Princess Aurora.
  • 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: Flora
Triple: [London Marathon, formerSponsor, Flora]
Generated description
Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Flora
Target entity description: Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
  • A. Flora
    Flora is a feminine given name of Latin origin meaning "flower," historically associated with the Roman goddess of flowers and spring.
  • B. Flora
    Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
  • C. Flora
    Flora is a celebrated 19th-century botanical illustration by Mary Evelyn Pickering that showcases her detailed and artistic rendering of plant life.
  • D. Flora
    Flora is one of the three good fairies in Disney's "Sleeping Beauty," known for her red attire, leadership among the fairies, and role in protecting Princess Aurora.
  • E. Flora
    Flora is the middle name of Ruth Disney, the daughter of Walt Disney and his wife Lillian.
  • 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_69ca836320e48190b5cf585b90a322c4 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fb7491c8190bcdb98d6cc003d9e completed March 31, 2026, 11:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6f658f248190957eba821b07cc4f completed April 3, 2026, 7:42 a.m.
NEDg Description generation batch_69cf713a184c8190b1fa788fd3ba8304 completed April 3, 2026, 7:50 a.m.
NED2 Entity disambiguation (via description) batch_69cf71d3517c819088c930ed468c4e8e completed April 3, 2026, 7:52 a.m.
Created at: March 30, 2026, 6:44 p.m.