Triple

T173330
Position Surface form Disambiguated ID Type / Status
Subject Tom Sawyer (1973 film) E3523 entity
Predicate stars P1956 FINISHED
Object Noah Keen
Noah Keen was a British character actor known for his numerous supporting roles in film and television from the 1950s through the 1990s.
 E35527 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: Noah Keen | Statement: [Tom Sawyer (1973 film), stars, Noah Keen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Noah Keen
Context triple: [Tom Sawyer (1973 film), stars, Noah Keen]
  • A. Marc Tarpenning
    Marc Tarpenning is an American engineer and entrepreneur best known as a co-founder of electric vehicle and clean energy company Tesla, Inc.
  • B. Liam
    Liam is a popular masculine given name of Irish origin, commonly understood as a short form of William.
  • C. Gavin
    Gavin is a masculine given name of Celtic origin, commonly used in English-speaking countries.
  • D. Zach Staenberg
    Zach Staenberg is an American film editor best known for his Academy Award–winning work on "The Matrix" and its sequels.
  • E. Bryce Dallas Howard
    Bryce Dallas Howard is an American actress and director known for roles in films such as "The Village," "Jurassic World," and "Rocketman," as well as for directing episodes of "The Mandalorian."
  • 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: Noah Keen
Triple: [Tom Sawyer (1973 film), stars, Noah Keen]
Generated description
Noah Keen was a British character actor known for his numerous supporting roles in film and television from the 1950s through the 1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Noah Keen
Target entity description: Noah Keen was a British character actor known for his numerous supporting roles in film and television from the 1950s through the 1990s.
  • A. Marc Tarpenning
    Marc Tarpenning is an American engineer and entrepreneur best known as a co-founder of electric vehicle and clean energy company Tesla, Inc.
  • B. Liam
    Liam is a popular masculine given name of Irish origin, commonly understood as a short form of William.
  • C. Gavin
    Gavin is a masculine given name of Celtic origin, commonly used in English-speaking countries.
  • D. Zach Staenberg
    Zach Staenberg is an American film editor best known for his Academy Award–winning work on "The Matrix" and its sequels.
  • E. Bryce Dallas Howard
    Bryce Dallas Howard is an American actress and director known for roles in films such as "The Village," "Jurassic World," and "Rocketman," as well as for directing episodes of "The Mandalorian."
  • 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_69a25374990081909766d30c79a18e0e completed Feb. 28, 2026, 2:31 a.m.
NER Named-entity recognition batch_69a258e1ec008190a89dd452f72574f4 completed Feb. 28, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a38f4c7dbc8190bd240d574dbe77ae completed March 1, 2026, 12:58 a.m.
NEDg Description generation batch_69a38fd6772081908bbaf308bdbcd5f6 completed March 1, 2026, 1:01 a.m.
NED2 Entity disambiguation (via description) batch_69a3908a50088190a7cea3de890a8e86 completed March 1, 2026, 1:04 a.m.
Created at: Feb. 28, 2026, 2:39 a.m.