Triple

T2727830
Position Surface form Disambiguated ID Type / Status
Subject Edison Studios E60234 entity
Predicate notableEmployee P304 FINISHED
Object Pearl White
Pearl White was a pioneering American silent film actress best known as the “Queen of the Serials” for her daring roles in early 20th-century adventure film series.
E292883 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 White | Statement: [Edison Studios, notableEmployee, Pearl White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pearl White
Context triple: [Edison Studios, notableEmployee, Pearl White]
  • A. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • B. Barbara
    Barbara is a station on Paris Métro Line 4 serving the southern suburbs of the French capital.
  • C. Gladys Brockwell
    Gladys Brockwell was an American stage and silent film actress known for her intense dramatic roles during the early 20th century.
  • D. Phyllis
    Phyllis is a 1970s American television sitcom, spun off from The Mary Tyler Moore Show, that stars Cloris Leachman as the widowed Phyllis Lindstrom starting a new life in San Francisco.
  • E. Bernice
    Bernice is a feminine given name most notably borne by Bernice King, the daughter of civil rights leaders Martin Luther King Jr. and Coretta Scott King.
  • 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 White
Triple: [Edison Studios, notableEmployee, Pearl White]
Generated description
Pearl White was a pioneering American silent film actress best known as the “Queen of the Serials” for her daring roles in early 20th-century adventure film series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pearl White
Target entity description: Pearl White was a pioneering American silent film actress best known as the “Queen of the Serials” for her daring roles in early 20th-century adventure film series.
  • A. Barbara
    Barbara is a station on Paris Métro Line 4 serving the southern suburbs of the French capital.
  • B. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • C. Gladys Brockwell
    Gladys Brockwell was an American stage and silent film actress known for her intense dramatic roles during the early 20th century.
  • D. Phyllis
    Phyllis is a 1970s American television sitcom, spun off from The Mary Tyler Moore Show, that stars Cloris Leachman as the widowed Phyllis Lindstrom starting a new life in San Francisco.
  • E. Bernice
    Bernice is a feminine given name most notably borne by Bernice King, the daughter of civil rights leaders Martin Luther King Jr. and Coretta Scott King.
  • 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_69ab4b75cd908190b691ef0d1801acda completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdacffa6481909df37335e8fdd595 completed March 7, 2026, 7:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb69aa8b081909c57e8a7f64d0913 completed March 10, 2026, 6:13 a.m.
NEDg Description generation batch_69afb717260c8190a93641152f163879 completed March 10, 2026, 6:15 a.m.
NED2 Entity disambiguation (via description) batch_69afb781327c819090c42c461d17762e completed March 10, 2026, 6:17 a.m.
Created at: March 6, 2026, 9:56 p.m.