Triple

T15011096
Position Surface form Disambiguated ID Type / Status
Subject Shark Tank E377836 entity
Predicate hasRecurringGuestInvestor P90709 FINISHED
Object Sara Blakely E404061 NE FINISHED

How this triple was built (2 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: Sara Blakely | Statement: [Shark Tank, hasRecurringGuestInvestor, Sara Blakely]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Blakely
Context triple: [Shark Tank, hasRecurringGuestInvestor, Sara Blakely]
  • A. Sara Blakely chosen
    Sara Blakely is an American entrepreneur and billionaire best known as the founder of the shapewear company Spanx.
  • B. Paige Mycoskie
    Paige Mycoskie is an American entrepreneur and designer best known as the founder of the vintage-inspired clothing and lifestyle brand Aviator Nation.
  • C. Sheryl Yoast
    Sheryl Yoast is a character in the film "Remember the Titans," depicted as the passionate, football-loving daughter of coach Bill Yoast.
  • D. Mary Kay Ash
    Mary Kay Ash was an American businesswoman and entrepreneur best known as the founder of Mary Kay Cosmetics, a pioneering direct-sales cosmetics company.
  • E. Sandy Lerner
    Sandy Lerner is an American businesswoman and philanthropist best known as the co-founder of networking giant Cisco Systems and later as a supporter of animal welfare, sustainable agriculture, and literary scholarship.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded734943481908dad4ceed4fe850c completed April 15, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe96a7dcac8190b0153d7cdac03afa completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:55 a.m.