Triple

T22663822
Position Surface form Disambiguated ID Type / Status
Subject Ma (2019 film) E559729 entity
Predicate stars P1956 FINISHED
Object Dante Brown
Dante Brown is an American actor known for his roles in film and television, including a starring role in the 2019 psychological horror film "Ma."
E1548609 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: Dante Brown | Statement: [Ma (2019 film), stars, Dante Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dante Brown
Context triple: [Ma (2019 film), stars, Dante Brown]
  • A. Dan Brown
    Dan Brown is an American author best known for his fast-paced mystery thrillers that blend historical, religious, and conspiracy themes, including the bestselling novel "The Da Vinci Code."
  • B. Dan Brown
    Dan Brown is an Australian musician best known as a guitarist for the metalcore band The Amity Affliction.
  • C. Dan Brownlie
    Dan Brownlie is an English football manager best known for managing non-league side Basingstoke Town F.C.
  • D. Thomas B. Harris
    Thomas B. Harris was a local figure of historical significance after whom the village of Thomasboro, Illinois, was named.
  • E. Theodore Winter
    Theodore Winter is a high-ranking CIA officer and the main antagonist in the 2010 action thriller film "Salt."
  • 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: Dante Brown
Triple: [Ma (2019 film), stars, Dante Brown]
Generated description
Dante Brown is an American actor known for his roles in film and television, including a starring role in the 2019 psychological horror film "Ma."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dante Brown
Target entity description: Dante Brown is an American actor known for his roles in film and television, including a starring role in the 2019 psychological horror film "Ma."
  • A. Dan Brown
    Dan Brown is an Australian musician best known as a guitarist for the metalcore band The Amity Affliction.
  • B. Dan Brown
    Dan Brown is an American author best known for his fast-paced mystery thrillers that blend historical, religious, and conspiracy themes, including the bestselling novel "The Da Vinci Code."
  • C. Dan Brownlie
    Dan Brownlie is an English football manager best known for managing non-league side Basingstoke Town F.C.
  • D. Thomas B. Harris
    Thomas B. Harris was a local figure of historical significance after whom the village of Thomasboro, Illinois, was named.
  • E. Theodore Winter
    Theodore Winter is a high-ranking CIA officer and the main antagonist in the 2010 action thriller film "Salt."
  • 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f176617ed8819095a58a2c9f1e3918 completed April 29, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73e409048190b435921e455d7bbd completed May 18, 2026, 8:17 p.m.
NEDg Description generation batch_6a0b7541919c8190a5bb0f31560bf871 completed May 18, 2026, 8:23 p.m.
NED2 Entity disambiguation (via description) batch_6a0b762f315c8190a85d804e26a6b1c5 completed May 18, 2026, 8:27 p.m.
Created at: April 17, 2026, 3:08 p.m.