Triple

T14212517
Position Surface form Disambiguated ID Type / Status
Subject The Keep E352265 entity
Predicate mainCharacter P1183 FINISHED
Object Howard
Howard is the protagonist of the horror novel "The Keep," around whom the story’s supernatural and psychological events revolve.
E1085961 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: Howard | Statement: [The Keep, mainCharacter, Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard
Context triple: [The Keep, mainCharacter, Howard]
  • A. Howard
    Howard is the middle name of William Howard Taft, the 27th president of the United States and later Chief Justice of the Supreme Court.
  • B. Howard
    Howard is the given name of the influential American film director, producer, and screenwriter Howard Hawks.
  • C. Howard
    Howard is a young boy who serves as a minor but symbolically important character in the play "Inherit the Wind," representing the town’s impressionable youth amid the evolution-versus-creationism trial.
  • D. Howard
    Howard is one of Sethe’s sons in Toni Morrison’s novel "Beloved," a child whose life is shaped by the trauma and legacy of slavery.
  • E. Howard
    Howard is the middle name of Robert H. Grubbs, the Nobel Prize–winning American chemist renowned for his work on olefin metathesis.
  • 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: Howard
Triple: [The Keep, mainCharacter, Howard]
Generated description
Howard is the protagonist of the horror novel "The Keep," around whom the story’s supernatural and psychological events revolve.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Howard
Target entity description: Howard is the protagonist of the horror novel "The Keep," around whom the story’s supernatural and psychological events revolve.
  • A. Howard
    Howard is one of Sethe’s sons in Toni Morrison’s novel "Beloved," a child whose life is shaped by the trauma and legacy of slavery.
  • B. Howard
    Howard is a fictional character best known as the romantic interest of Marina in their shared narrative.
  • C. Howard
    Howard is a young boy who serves as a minor but symbolically important character in the play "Inherit the Wind," representing the town’s impressionable youth amid the evolution-versus-creationism trial.
  • D. Howard
    Howard is a character in Kenneth Lonergan's play "The Waverly Gallery," serving as a key figure in the story's exploration of family, memory, and aging.
  • E. Howard
    Howard is a seasoned, wise old prospector in the classic 1948 film "The Treasure of the Sierra Madre," known for his experience, moral insight, and pivotal role in the gold-hunting expedition.
  • 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_69d8278a06e481908b5d6af0a8afe737 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de620dba0c8190bb77a1df10e1d3a7 completed April 14, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd19574280819091bafd95a75983bf completed May 7, 2026, 10:59 p.m.
NEDg Description generation batch_69fd1a231cbc819083d38e25073892bf completed May 7, 2026, 11:02 p.m.
NED2 Entity disambiguation (via description) batch_69fd1ada47788190afcf8078d76ef339 completed May 7, 2026, 11:06 p.m.
Created at: April 10, 2026, 1:05 a.m.