Triple

T12358161
Position Surface form Disambiguated ID Type / Status
Subject Harold Lee E294663 entity
Predicate hasRomanticPartner P9994 FINISHED
Object Maria
Maria is a fictional character who serves as the love interest of Harold Lee in the "Harold & Kumar" comedy film series.
E978049 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: Maria | Statement: [Harold Lee, hasRomanticPartner, Maria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria
Context triple: [Harold Lee, hasRomanticPartner, Maria]
  • A. Maria
    Maria is an Italian woman best known as the younger sister of actress Sophia Loren and the former wife of film producer Romano Mussolini.
  • B. Maria
    Maria is a character in the period drama film "Stage Beauty," which explores gender roles and the world of 17th-century English theatre.
  • C. Maria
    Maria is a track on Rage Against the Machine’s 2000 album "The Battle of Los Angeles," known for its politically charged lyrics and aggressive rap metal sound.
  • D. Maria
    Maria I of Portugal was the first queen regnant of Portugal, known for her devout Catholicism, initial period of enlightened reforms, and later mental illness that led to her son acting as regent.
  • E. Maria
    Maria is a witty and sharp-tongued lady-in-waiting to the Princess of France in William Shakespeare’s comedy "Love's Labour's Lost."
  • 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: Maria
Triple: [Harold Lee, hasRomanticPartner, Maria]
Generated description
Maria is a fictional character who serves as the love interest of Harold Lee in the "Harold & Kumar" comedy film series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maria
Target entity description: Maria is a fictional character who serves as the love interest of Harold Lee in the "Harold & Kumar" comedy film series.
  • A. Maria
    Maria is a friendly human character from Sesame Street known for her warm personality and close relationships with the show's Muppet residents.
  • B. Maria
    Maria is a key character in the historical drama "Tulip Fever," serving as the young maid whose secret romance and pregnancy help drive the film’s central scheme and emotional stakes.
  • C. Maria
    Maria is a friendly human character on Sesame Street who often interacts with Big Bird and the other residents of the neighborhood.
  • D. Maria
    Maria is a central character in the film "An Ordinary Couple," whose personal viewpoint shapes how the story’s everyday relationship dynamics are experienced and understood.
  • E. Maria
    Maria is a central character in Fritz Lang's classic science fiction film "Metropolis," known for her compassionate leadership and symbolic role as a mediator between social classes.
  • 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_69d6ab6d8a4081908636601e69ddf262 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f8e64dc81908c2242c68cd1b86e completed April 10, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62a97614c8190b67e07df3e424e32 completed May 2, 2026, 4:47 p.m.
NEDg Description generation batch_69f62be4de888190aac94d441748d295 completed May 2, 2026, 4:52 p.m.
NED2 Entity disambiguation (via description) batch_69f62d4d0b8881908aa6b67db7d14609 completed May 2, 2026, 4:58 p.m.
Created at: April 8, 2026, 9:54 p.m.