Triple

T19876449
Position Surface form Disambiguated ID Type / Status
Subject Enola E477649 entity
Predicate protectedBy P957 FINISHED
Object Helen
Helen is a protective figure, likely a guardian or caretaker, known for safeguarding Enola.
E477648 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: [Enola, protectedBy, Helen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen
Context triple: [Enola, protectedBy, Helen]
  • A. Helen
    Helen is a central character in Ernest Hemingway’s short story “The Snows of Kilimanjaro,” portrayed as the wealthy, devoted wife and companion of the writer Harry during his final, reflective days in Africa.
  • B. Helen
    Helen is the given name of H. T. Lowe-Porter, the American translator best known for bringing Thomas Mann’s works into English.
  • C. Helen
    Helen is the daring, quick-thinking heroine of the early 20th-century silent film serial "The Hazards of Helen," known for her action-packed, stunt-filled adventures.
  • D. Helen
    Helen is the birth name of British television presenter Tess Daly, best known for co-hosting the BBC dance competition show "Strictly Come Dancing."
  • E. Helen
    Helen is a Greek and Danish princess of the early 20th century, known as Princess Helen of Greece and Denmark.
  • 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: [Enola, protectedBy, Helen]
Generated description
Helen is a protective figure, likely a guardian or caretaker, known for safeguarding Enola.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Helen
Target entity description: Helen is a protective figure, likely a guardian or caretaker, known for safeguarding Enola.
  • A. Helen
    Helen is a fictional protagonist associated with a narrative set in or around New York City's Central Park.
  • B. Helen chosen
    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.
  • C. Helen
    Helen is a person characterized in this context by her adversarial relationship with Deacon.
  • 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 a figure from Greek mythology famed for her extraordinary beauty, whose abduction by Paris sparked the Trojan War.
  • F. None of above.

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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658dbdb648190b423865e7994a8fe completed April 20, 2026, 4:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07dbc82f0881909556c54b8ce3533f completed May 16, 2026, 2:51 a.m.
NEDg Description generation batch_6a07dc854a0c8190b0da81ead6b9cfc1 completed May 16, 2026, 2:55 a.m.
NED2 Entity disambiguation (via description) batch_6a07dd45e93c8190b14c23487398a8ec completed May 16, 2026, 2:58 a.m.
Created at: April 10, 2026, 1:52 p.m.