Triple

T10387597
Position Surface form Disambiguated ID Type / Status
Subject Deacon E244803 entity
Predicate enemyOf P437 FINISHED
Object Helen
Helen is a person characterized in this context by her adversarial relationship with Deacon.
E858886 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: Helen | Statement: [Deacon, enemyOf, Helen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen
Context triple: [Deacon, enemyOf, Helen]
  • A. Helen
    Helen is the birth name of P. L. Travers, the Australian-British author best known for creating the "Mary Poppins" series.
  • B. Helen
    Helen is the given first name of Violet Bonham Carter, a prominent British Liberal politician and orator of the 20th century.
  • C. Helen
    Helen is a central survivor and maternal figure in the post-apocalyptic film "Waterworld," known for her determination to protect the child Enola and seek the mythical Dryland.
  • D. Helen
    Helen is the central character in the novel "The Spare Room," around whom the story’s emotional and narrative developments revolve.
  • E. Helen
    Helen is the given name of H. T. Lowe-Porter, the American translator best known for bringing Thomas Mann’s works into English.
  • 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: Helen
Triple: [Deacon, enemyOf, Helen]
Generated description
Helen is a person characterized in this context by her adversarial relationship with Deacon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Helen
Target entity description: Helen is a person characterized in this context by her adversarial relationship with Deacon.
  • A. Helen
    Helen is a fictional protagonist associated with a narrative set in or around New York City's Central Park.
  • B. Helen
    Helen is a figure from Greek mythology famed for her extraordinary beauty, whose abduction by Paris sparked the Trojan War.
  • C. Helen
    Helen is a character from the British television sitcom "Out of This World."
  • D. Helen
    Helen is the given name of Maria Helen Van Schaack, likely used as her primary personal name.
  • E. Helen
    Helen is a fictional character from the 1930 aviation war film "Hell's Angels," which is renowned for its groundbreaking aerial combat sequences and early sound-era spectacle.
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9a59d688190b1da1ea0ed48fafa completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d795aa3afc8190aed1ca11556ae34f completed April 9, 2026, 12:03 p.m.
NEDg Description generation batch_69d7989cc318819083f325f4b223cf71 completed April 9, 2026, 12:16 p.m.
NED2 Entity disambiguation (via description) batch_69d799917ab881909a947ad8059652c6 completed April 9, 2026, 12:20 p.m.
Created at: April 6, 2026, 12:05 p.m.