Triple

T10194634
Position Surface form Disambiguated ID Type / Status
Subject Pet E238129 entity
Predicate starring P1507 FINISHED
Object Janet Song
Janet Song is an actress known for her role in the psychological thriller film "Pet."
E847604 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: Janet Song | Statement: [Pet, starring, Janet Song]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet Song
Context triple: [Pet, starring, Janet Song]
  • A. Cheryl Song
    Cheryl Song is an American dancer and actress best known as a featured Soul Train dancer who also appeared in the 1988 action film "Action Jackson."
  • B. Laura Sohn
    Laura Sohn is an American actress best known for her role as FBI agent Alina Park on the television series "The Blacklist."
  • C. Christina Oh
    Christina Oh is an American film producer best known for her work on acclaimed independent films, including the Oscar-nominated drama "Minari."
  • D. Joie Lee
    Joie Lee is an American actress, screenwriter, and producer best known for her frequent collaborations with her brother Spike Lee in films exploring African-American life and culture.
  • E. Amy Chiang
    Amy Chiang is a member of Taiwan’s influential Chiang family, known primarily as a daughter of former President Chiang Ching-kuo.
  • 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: Janet Song
Triple: [Pet, starring, Janet Song]
Generated description
Janet Song is an actress known for her role in the psychological thriller film "Pet."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Janet Song
Target entity description: Janet Song is an actress known for her role in the psychological thriller film "Pet."
  • A. Cheryl Song
    Cheryl Song is an American dancer and actress best known as a featured Soul Train dancer who also appeared in the 1988 action film "Action Jackson."
  • B. Laura Sohn
    Laura Sohn is an American actress best known for her role as FBI agent Alina Park on the television series "The Blacklist."
  • C. Christina Oh
    Christina Oh is an American film producer best known for her work on acclaimed independent films, including the Oscar-nominated drama "Minari."
  • D. Joie Lee
    Joie Lee is an American actress, screenwriter, and producer best known for her frequent collaborations with her brother Spike Lee in films exploring African-American life and culture.
  • E. Amy Chiang
    Amy Chiang is a member of Taiwan’s influential Chiang family, known primarily as a daughter of former President Chiang Ching-kuo.
  • 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_69ca84de1b208190bf17bb305b002605 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdedc7cc748190bceb8f657afcc054 completed April 2, 2026, 4:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d317dbfb7c819087aafc7161b14707 completed April 6, 2026, 2:18 a.m.
NEDg Description generation batch_69d319670c6c8190b77257340ec8e6d4 completed April 6, 2026, 2:24 a.m.
NED2 Entity disambiguation (via description) batch_69d31d371e948190ac6d31daad2afbdf completed April 6, 2026, 2:40 a.m.
Created at: March 30, 2026, 9:13 p.m.