Triple

T8243990
Position Surface form Disambiguated ID Type / Status
Subject The Ledge E192804 entity
Predicate antagonist P4675 FINISHED
Object Cressner
Cressner is the sadistic, wealthy gambler and primary villain in Stephen King’s short story “The Ledge,” known for forcing a man to risk his life by walking around a narrow ledge high above the city.
 E721773 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: Cressner | Statement: [The Ledge, antagonist, Cressner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cressner
Context triple: [The Ledge, antagonist, Cressner]
  • A. Crouse
    Crouse is a surname most notably associated with American actress Lindsay Crouse and her family.
  • B. Lockweiler
    Lockweiler is a village-level district within the town of Wadern in the Saarland region of Germany.
  • C. Thierstein
    Thierstein is a district in the canton of Solothurn in northwestern Switzerland, comprising several municipalities near the French border.
  • D. Cresserons
    Cresserons is a small commune in the Calvados department of the Normandy region in northwestern France.
  • E. Vanselow
    Vanselow is a German-language surname borne by various individuals, including figures such as Ernst Vanselow.
  • 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: Cressner
Triple: [The Ledge, antagonist, Cressner]
Generated description
Cressner is the sadistic, wealthy gambler and primary villain in Stephen King’s short story “The Ledge,” known for forcing a man to risk his life by walking around a narrow ledge high above the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cressner
Target entity description: Cressner is the sadistic, wealthy gambler and primary villain in Stephen King’s short story “The Ledge,” known for forcing a man to risk his life by walking around a narrow ledge high above the city.
  • A. Crouse
    Crouse is a surname most notably associated with American actress Lindsay Crouse and her family.
  • B. Lockweiler
    Lockweiler is a village-level district within the town of Wadern in the Saarland region of Germany.
  • C. Thierstein
    Thierstein is a district in the canton of Solothurn in northwestern Switzerland, comprising several municipalities near the French border.
  • D. Cresserons
    Cresserons is a small commune in the Calvados department of the Normandy region in northwestern France.
  • E. Vanselow
    Vanselow is a German-language surname borne by various individuals, including figures such as Ernst Vanselow.
  • 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_69ca82de7b8c81908d8106f8a53cff9b completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb78711f5081909c2f357334491a07 completed March 31, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd3521bfb48190935fe82a1f768adc completed April 1, 2026, 3:09 p.m.
NEDg Description generation batch_69cd37a5d3bc8190801b1b0f09eee462 completed April 1, 2026, 3:20 p.m.
NED2 Entity disambiguation (via description) batch_69cd4edfda788190a29f5d9a7a61f6ed completed April 1, 2026, 4:59 p.m.
Created at: March 30, 2026, 5:47 p.m.