Triple

T4609716
Position Surface form Disambiguated ID Type / Status
Subject Horror of Dracula E100524 entity
Predicate starring P1507 FINISHED
Object Carol Marsh
Carol Marsh was a British actress best known for her role in classic mid-20th-century horror cinema.
E522595 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: Carol Marsh | Statement: [Horror of Dracula, starring, Carol Marsh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Marsh
Context triple: [Horror of Dracula, starring, Carol Marsh]
  • A. Carol Richards
    Carol Richards was an American singer best remembered for her popular mid-20th-century vocal performances, including classic holiday recordings.
  • B. Barbara Trentham
    Barbara Trentham was an American model and actress who later became a painter, known in part for her marriage to British comedian John Cleese.
  • C. Ann Sadler
    Ann Sadler was the wife of John Harvard, the English clergyman and benefactor after whom Harvard University is named.
  • D. Helen Melland
    Helen Melland was the wife of British Prime Minister Herbert Henry Asquith and a member of the English upper-middle class in the late 19th century.
  • E. Helen Thomson
    Helen Thomson is an Australian actress known for her work in film, television, and theatre, including a prominent role in the biographical drama "Elvis" (2022).
  • 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: Carol Marsh
Triple: [Horror of Dracula, starring, Carol Marsh]
Generated description
Carol Marsh was a British actress best known for her role in classic mid-20th-century horror cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carol Marsh
Target entity description: Carol Marsh was a British actress best known for her role in classic mid-20th-century horror cinema.
  • A. Carol Richards
    Carol Richards was an American singer best remembered for her popular mid-20th-century vocal performances, including classic holiday recordings.
  • B. Barbara Trentham
    Barbara Trentham was an American model and actress who later became a painter, known in part for her marriage to British comedian John Cleese.
  • C. Ann Sadler
    Ann Sadler was the wife of John Harvard, the English clergyman and benefactor after whom Harvard University is named.
  • D. Helen Melland
    Helen Melland was the wife of British Prime Minister Herbert Henry Asquith and a member of the English upper-middle class in the late 19th century.
  • E. Helen Thomson
    Helen Thomson is an Australian actress known for her work in film, television, and theatre, including a prominent role in the biographical drama "Elvis" (2022).
  • 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_69bd43cce1e08190a07d53af6a9b6c24 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd599f08d88190ad4bed8bafb592cd completed March 20, 2026, 2:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf486aabac8190a90b4402403078ac completed March 22, 2026, 1:39 a.m.
NEDg Description generation batch_69bf49c434c88190acf6058e2805ee0f completed March 22, 2026, 1:45 a.m.
NED2 Entity disambiguation (via description) batch_69bf4a2c4748819080df9bb468fd9198 completed March 22, 2026, 1:47 a.m.
Created at: March 20, 2026, 1:12 p.m.