Triple

T12225448
Position Surface form Disambiguated ID Type / Status
Subject Agnes Moorehead E291337 entity
Predicate notableRole P22 FINISHED
Object Endora
Endora is the sardonic, magically powerful mother-in-law witch from the classic American television sitcom "Bewitched."
 E972768 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: Endora | Statement: [Agnes Moorehead, notableRole, Endora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Endora
Context triple: [Agnes Moorehead, notableRole, Endora]
  • A. Endora
    Endora is the fictional small-town setting of the film "What's Eating Gilbert Grape," characterized by its rural isolation and close-knit community.
  • B. Mathilda
    Mathilda is the middle name of Elivera Mathilda Carlson Doud, the wife of former U.S. President Dwight D. Eisenhower.
  • C. Mathilda
    Mathilda is the young girl in the film "Léon: The Professional" who becomes the protégé of a solitary hitman after her family is murdered.
  • D. Celia
    Celia is a 2020 Afrobeats and R&B studio album by Nigerian singer Tiwa Savage that blends contemporary African pop with global influences.
  • E. Celia
    Celia is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • 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: Endora
Triple: [Agnes Moorehead, notableRole, Endora]
Generated description
Endora is the sardonic, magically powerful mother-in-law witch from the classic American television sitcom "Bewitched."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Endora
Target entity description: Endora is the sardonic, magically powerful mother-in-law witch from the classic American television sitcom "Bewitched."
  • A. Endora
    Endora is the fictional small-town setting of the film "What's Eating Gilbert Grape," characterized by its rural isolation and close-knit community.
  • B. Mathilda
    Mathilda is the middle name of Elivera Mathilda Carlson Doud, the wife of former U.S. President Dwight D. Eisenhower.
  • C. Mathilda
    Mathilda is the young girl in the film "Léon: The Professional" who becomes the protégé of a solitary hitman after her family is murdered.
  • D. Celia
    Celia is a 2020 Afrobeats and R&B studio album by Nigerian singer Tiwa Savage that blends contemporary African pop with global influences.
  • E. Celia
    Celia is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ca11f788190bad2efb6c83ffccb completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aa9023881909f8373e02d2cad4b completed May 2, 2026, 2:31 p.m.
NEDg Description generation batch_69f61a13fd1481908a06ca65b276e0e1 completed May 2, 2026, 3:36 p.m.
NED2 Entity disambiguation (via description) batch_69f61ad2bd0c8190ada37bc1f8ae160f completed May 2, 2026, 3:40 p.m.
Created at: April 8, 2026, 9:51 p.m.