Triple

T17945293
Position Surface form Disambiguated ID Type / Status
Subject Amethyst E448687 entity
Predicate closeFriend P8712 FINISHED
Object Pearl
Pearl is a meticulous, intelligent Gem from the animated series "Steven Universe," known for her loyalty, precision in combat, and complex emotional growth.
E447798 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: Pearl | Statement: [Amethyst, closeFriend, Pearl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pearl
Context triple: [Amethyst, closeFriend, Pearl]
  • A. Pearl
    "Pearl" is a Middle English alliterative poem, often attributed to the anonymous "Pearl Poet," renowned for its intricate structure and spiritual meditation on loss and salvation.
  • B. Pearl
    Pearl is the enigmatic and spirited daughter of Hester Prynne in Nathaniel Hawthorne’s novel *The Scarlet Letter*, symbolizing both sin and redemption.
  • C. Pearl
    "Pearl" is a lesser-known work by screenwriter Stirling Silliphant, likely a film or television script reflecting his characteristic dramatic storytelling.
  • D. Pearl
    Pearl is the nickname of Dwayne "Pearl" Washington, a celebrated American basketball player known for his flashy ball-handling and standout college career at Syracuse University.
  • E. Pearl
    Pearl is a British actress best known for playing Bill Potts, a companion of the Doctor, in the long-running television series "Doctor Who."
  • 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: Pearl
Triple: [Amethyst, closeFriend, Pearl]
Generated description
Pearl is a meticulous, intelligent Gem from the animated series "Steven Universe," known for her loyalty, precision in combat, and complex emotional growth.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pearl
Target entity description: Pearl is a meticulous, intelligent Gem from the animated series "Steven Universe," known for her loyalty, precision in combat, and complex emotional growth.
  • A. Pearl chosen
    Pearl is a central character in the animated series "Steven Universe," depicted as a meticulous, graceful Gem warrior who serves as a mentor and guardian to Steven.
  • B. Pearl
    Pearl is the enigmatic and spirited daughter of Hester Prynne in Nathaniel Hawthorne’s novel *The Scarlet Letter*, symbolizing both sin and redemption.
  • C. Pearl
    Pearl is the anthropomorphized first-class observation coach and one of the main train characters in Andrew Lloyd Webber’s musical "Starlight Express."
  • D. Pearl
    Pearl is a student associated with Mr. Ray, likely in an educational or mentorship context.
  • E. Pearl
    Pearl is a British actress best known for playing Bill Potts, a companion of the Doctor, in the long-running television series "Doctor Who."
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad990b948190a5e6fd50a15f64e3 completed April 19, 2026, 10:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0397ebabcc81908e6cfe983afcb943 completed May 12, 2026, 9:13 p.m.
NEDg Description generation batch_6a0399364d988190a457415c9c64a68d completed May 12, 2026, 9:18 p.m.
NED2 Entity disambiguation (via description) batch_6a0399e221308190988e728b9efb0141 completed May 12, 2026, 9:21 p.m.
Created at: April 10, 2026, 10:21 a.m.