Triple

T7438426
Position Surface form Disambiguated ID Type / Status
Subject ZaSu Pitts E171679 entity
Predicate givenName P17 FINISHED
Object Susan
Susan is the given name of American actress ZaSu Pitts, a prominent comedic and dramatic film star of the silent and early sound eras.
 E664530 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: Susan | Statement: [ZaSu Pitts, givenName, Susan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Susan
Context triple: [ZaSu Pitts, givenName, Susan]
  • A. Susan
    Susan is the middle name of Olivia Susan Clemens.
  • B. Susan
    Susan is the birth name of American actress Sigourney Weaver, renowned for her iconic roles in science fiction and horror films such as the Alien franchise.
  • C. Susan
    Susan is a supporting character in the "Nosedive" episode of the anthology television series Black Mirror.
  • D. Susan
    Susan "Suze" Rotolo was an American artist and political activist best known as Bob Dylan’s early 1960s girlfriend and the woman pictured with him on the cover of his album "The Freewheelin’ Bob Dylan."
  • E. Susan
    Susan is the given name of American actress Susan Kelechi Watson, known for her role as Beth Pearson on the television series "This Is Us."
  • 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: Susan
Triple: [ZaSu Pitts, givenName, Susan]
Generated description
Susan is the given name of American actress ZaSu Pitts, a prominent comedic and dramatic film star of the silent and early sound eras.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Susan
Target entity description: Susan is the given name of American actress ZaSu Pitts, a prominent comedic and dramatic film star of the silent and early sound eras.
  • A. Susan
    Susan is the given name of Susan B. Anthony, a leading American social reformer and key figure in the women’s suffrage movement.
  • B. Susan
    Susan is the birth name of American actress Sigourney Weaver, renowned for her iconic roles in science fiction and horror films such as the Alien franchise.
  • C. Susan
    Susan is the given name of the American writer, filmmaker, and political activist Susan Sontag, renowned for her influential essays on culture and aesthetics.
  • D. Susan
    Susan is the given name of American actress Susan Kelechi Watson, known for her role as Beth Pearson on the television series "This Is Us."
  • E. Susan
    Susan is the given name of American painter and photographer Susan Macdowell Eakins, known for her portraits and still lifes.
  • 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_69c68a64228c8190affaec2a8127ce7b completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f34aa3388190ac300cf934042d78 completed March 27, 2026, 9:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8278cd9cc8190b88767c1432b3007 completed March 28, 2026, 7:10 p.m.
NEDg Description generation batch_69c828854f6c8190885afb60d789f9b9 completed March 28, 2026, 7:14 p.m.
NED2 Entity disambiguation (via description) batch_69c82926c16c8190adf364f7b9d3c149 completed March 28, 2026, 7:16 p.m.
Created at: March 27, 2026, 3:13 p.m.