Triple

T12698927
Position Surface form Disambiguated ID Type / Status
Subject Life as a House E303405 entity
Predicate screenwriter P2831 FINISHED
Object Mark Andrus
Mark Andrus is an American screenwriter best known for co-writing the acclaimed film "As Good as It Gets."
E997615 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: Mark Andrus | Statement: [Life as a House, screenwriter, Mark Andrus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Andrus
Context triple: [Life as a House, screenwriter, Mark Andrus]
  • A. Trent Olsen
    Trent Olsen is an American former child actor and the older brother of actresses Mary-Kate, Ashley, and Elizabeth Olsen.
  • B. Darren Lemke
    Darren Lemke is an American screenwriter and film producer known for working on fantasy and adventure films such as Jack the Giant Slayer and the Goosebumps movie adaptation.
  • C. Matt Oberg
    Matt Oberg is an American actor and comedian known for his work in television comedies and voice acting roles.
  • D. D.J. Grothe
    D.J. Grothe is an American skeptic, speaker, and former president of the James Randi Educational Foundation known for promoting critical thinking and secular humanism.
  • E. Trent Burns
    Trent Burns is the reclusive, working-class lawn caretaker who forms an unlikely and transformative friendship with a wealthy young girl in the film "Lawn Dogs."
  • 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: Mark Andrus
Triple: [Life as a House, screenwriter, Mark Andrus]
Generated description
Mark Andrus is an American screenwriter best known for co-writing the acclaimed film "As Good as It Gets."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mark Andrus
Target entity description: Mark Andrus is an American screenwriter best known for co-writing the acclaimed film "As Good as It Gets."
  • A. Trent Olsen
    Trent Olsen is an American former child actor and the older brother of actresses Mary-Kate, Ashley, and Elizabeth Olsen.
  • B. Darren Lemke
    Darren Lemke is an American screenwriter and film producer known for working on fantasy and adventure films such as Jack the Giant Slayer and the Goosebumps movie adaptation.
  • C. Matt Oberg
    Matt Oberg is an American actor and comedian known for his work in television comedies and voice acting roles.
  • D. D.J. Grothe
    D.J. Grothe is an American skeptic, speaker, and former president of the James Randi Educational Foundation known for promoting critical thinking and secular humanism.
  • E. Trent Burns
    Trent Burns is the reclusive, working-class lawn caretaker who forms an unlikely and transformative friendship with a wealthy young girl in the film "Lawn Dogs."
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ed26588190ae76ff17159e06ec completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671b066348190aedfe186fc4724f9 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f672d16f8881908c6d5cfed0b3ec3a completed May 2, 2026, 9:55 p.m.
NED2 Entity disambiguation (via description) batch_69f67396fdac8190970068b2c39ad2f7 completed May 2, 2026, 9:58 p.m.
Created at: April 9, 2026, 5:22 p.m.