Triple

T2951996
Position Surface form Disambiguated ID Type / Status
Subject See's Candies E79840 entity
Predicate foundedBy P104 FINISHED
Object Mary See
Mary See was an American candy maker whose recipes and image became the iconic foundation of the See's Candies chocolate and confectionery brand.
 E313820 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: Mary See | Statement: [See's Candies, foundedBy, Mary See]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mary See
Context triple: [See's Candies, foundedBy, Mary See]
  • A. Myra
    Myra was an ancient Greek city in Lycia, in what is now southwestern Turkey, historically notable as a major early Christian center and the bishopric of Saint Nicholas.
  • B. Myra
    Myra is a feminine given name used in various cultures, often associated with individuals of Jewish and English-speaking backgrounds.
  • C. Tulsi Lake
    Tulsi Lake is a freshwater reservoir on Salsette Island in Mumbai, India, that serves as one of the city's important sources of drinking water.
  • D. Erin
    Erin Jobs is the daughter of Apple co-founder Steve Jobs and his wife Laurene Powell Jobs.
  • E. Erin
    Erin is a feminine given name commonly used in English-speaking countries, often associated with the poetic name for Ireland.
  • 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: Mary See
Triple: [See's Candies, foundedBy, Mary See]
Generated description
Mary See was an American candy maker whose recipes and image became the iconic foundation of the See's Candies chocolate and confectionery brand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mary See
Target entity description: Mary See was an American candy maker whose recipes and image became the iconic foundation of the See's Candies chocolate and confectionery brand.
  • A. Myra
    Myra is a feminine given name used in various cultures, often associated with individuals of Jewish and English-speaking backgrounds.
  • B. Myra
    Myra was an ancient Greek city in Lycia, in what is now southwestern Turkey, historically notable as a major early Christian center and the bishopric of Saint Nicholas.
  • C. Tulsi Lake
    Tulsi Lake is a freshwater reservoir on Salsette Island in Mumbai, India, that serves as one of the city's important sources of drinking water.
  • D. Erin
    Erin Jobs is the daughter of Apple co-founder Steve Jobs and his wife Laurene Powell Jobs.
  • E. Erin
    Erin is a feminine given name commonly used in English-speaking countries, often associated with the poetic name for Ireland.
  • 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_69ad8b1276588190a374a0b12e0f7bdf completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad98fcea5c8190b7d80de942bcb4f7 completed March 8, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc7edc808190863ec8f99efa3875 completed March 11, 2026, 5:24 a.m.
NEDg Description generation batch_69b0fd7d1cc88190a4f533a92d7e6de3 completed March 11, 2026, 5:28 a.m.
NED2 Entity disambiguation (via description) batch_69b0fde74b608190b59da720c90adfeb completed March 11, 2026, 5:30 a.m.
Created at: March 8, 2026, 2:57 p.m.